update

README.md

@@ -0,0 +1,219 @@
+---
+license: cc-by-nc-4.0
+language:
+- de
+- en
+base_model: openai/whisper-large-v3
+metrics:
+- cer
+- wer
+pipeline_tag: automatic-speech-recognition
+library_name: transformers
+---
+# CrisperWhisper
+
+**CrisperWhisper** is an advanced variant of OpenAI's Whisper, designed for fast, precise, and verbatim speech recognition with accurate (**crisp**) word-level timestamps. Unlike the original Whisper, which tends to omit disfluencies and follows more of a intended transcription style, CrisperWhisper aims to transcribe every spoken word exactly as it is, including fillers, pauses, stutters and false starts. Checkout our repo for more details: https://github.com/nyrahealth/CrisperWhisper/blob/develop/README.md
+
+## Key Features
+
+- 🎯 **Accurate Word-Level Timestamps**: Provides precise timestamps, even around disfluencies and pauses, by utilizing an adjusted tokenizer and a custom attention loss during training.
+- 📝 **Verbatim Transcription**: Transcribes every spoken word exactly as it is, including and differentiating fillers like "um" and "uh".
+- 🔍 **Filler Detection**: Detects and accurately transcribes fillers.
+- 🛡️ **Hallucination Mitigation**: Minimizes transcription hallucinations to enhance accuracy.
+
+## Table of Contents
+
+- [Key Features](#key-features)
+- [Highlights](#highlights)
+- [Performance Overview](#1-performance-overview)
+  - [Qualitative Performance Overview](#11-qualitative-performance-overview)
+  - [Quantitative Performance Overview](#12-quantitative-performance-overview)
+    - [Transcription Performance](#transcription-performance)
+    - [Segmentation Performance](#segmentation-performance)
+- [Usage](#2-usage)
+  - [with transformers](#21-usage-with-🤗-transformers)
+- [How?](#3-How?)
+
+
+## Highlights
+
+- 🏆 **1st place** on the [OpenASR Leaderboard](https://huggingface.co/spaces/hf-audio/open_asr_leaderboard) in verbatim datasets (TED, AMI) 
+- 🎓 **Accepted at INTERSPEECH 2024**.
+- 📄 **Paper Drop**: Check out our [paper](https://arxiv.org/abs/2408.16589) for details and reasoning behind our tokenizer adjustment.
+- ✨ **New Feature**: Not mentioned in the paper is a added AttentionLoss to further improve timestamp accuracy. By specifically adding a loss to train the attention scores used for the DTW alignment using timestamped data we significantly boosted the alignment performance. 
+
+
+
+## 1. Performance Overview
+
+### 1.1 Qualitative Performance Overview
+
+
+| Audio | Whisper Large V3 | Crisper Whisper |
+|-------|------------------------|------------------------|
+| [Demo de 1](https://github.com/user-attachments/assets/c8608ca8-5e02-4c4a-afd3-8f7c5bff75d5) | Er war kein Genie, aber doch ein fähiger Ingenieur. | Es ist zwar kein. Er ist zwar kein Genie, aber doch ein fähiger Ingenieur.|
+| [Demo de 2](https://github.com/user-attachments/assets/c68414b1-0f84-441c-b39b-29069487edb6) | Leider müssen wir in diesen schweren Zeiten auch unserem Tagesgeschäft nachgehen. Der hier vorgelegte Kulturhaushalt der Ampelregierung strebt an, den Erfolgskurs der Union zumindest fiskalisch fortzuführen. | Leider [UH] müssen wir in diesen [UH] schweren Zeiten auch [UH] unserem [UH] Tagesgeschäft nachgehen. Der hier [UH] vorgelegte [UH] Kulturhaushalt der [UH] Ampelregierung strebt an, den [UH] Erfolgskurs der Union [UH] zumindest [UH] fiskalisch fortzuführen. Es. |
+| [Demo de 3](https://github.com/user-attachments/assets/0c1ed60c-2829-47e4-b7ba-eb584b0a5e9a) | die über alle FRA-Fraktionen hinweg gut im Blick behalten sollten, auch weil sie teilweise sehr teeteuer sind. Aber nicht nur, weil sie teeteuer sind. Wir steigen mit diesem Endentwurf ein in die sogenannten Pandemie-Bereitschaftsverträge.| Die über alle Fr Fraktionen hinweg gut im [UH] Blick behalten sollten, auch weil sie teil teilweise sehr te teuer sind. Aber nicht nur, weil sie te teuer sind. Wir [UH] steigen mit diesem Ent Entwurf ein in die sogenannten Pand Pandemiebereitschaftsverträge. |
+| [Demo en 1](https://github.com/user-attachments/assets/cde5d69c-657f-4ae4-b4ae-b958ea2eacc5) | alternative is you can get like, you have those Dr. Bronner's| Alternative is you can get like [UH] you have those, you know, those doctor Brahmer's. |
+| [Demo en 2](https://github.com/user-attachments/assets/906e307d-5613-4c41-9c61-65f4beede1fd) | influence our natural surrounding? How does it influence our ecosystem? | Influence our [UM] our [UH] our natural surrounding. How does it influence our ecosystem? |
+| [Demo en 3](https://github.com/user-attachments/assets/6c09cd58-a574-4697-9a7e-92e416cf2522) | and always find a place on the street to park and it was easy and you weren't a long distance away from wherever it was that you were trying to go. So I remember that being a lot of fun and easy to do and there were nice places to go and good events to attend. Come downtown and you had the Warner Theater and | And always find a place on the street to park. And and it was it was easy and you weren't a long distance away from wherever it was that you were trying to go. So, I I I remember that being a lot of fun and easy to do and there were nice places to go and, [UM] i good events to attend. Come downtown and you had the Warner Theater and, [UM] |
+| [Demo en 4](https://github.com/user-attachments/assets/7df19486-5e4e-4443-8528-09b07dddf61a) | you know, more masculine, who were rough, and that definitely wasn't me. Then, you know, I was very smart because my father made sure I was smart, you know. So, you know, I hung around those people, you know. And then you had the ones that were just out doing things that they shouldn't have been doing also. So, yeah, I was in the little geek squad. You were in the little geek squad. Yeah. | you know, more masculine, who were rough, and that definitely wasn't me. Then, you know, I was very smart because my father made sure I was smart. You know, so, [UM] you know, I I hung around those people, you know. And then you had the ones that were just just out doing things that they shouldn't have been doing also. So yeah, I was the l I was in the little geek squad. Do you |
+
+### 1.2 Quantitative Performance Overview
+
+#### Transcription Performance
+
+CrisperWhisper significantly outperforms Whisper Large v3, especially on datasets that have a more verbatim transcription style in the ground truth, such as AMI and TED-LIUM.
+
+| Dataset            | CrisperWhisper | Whisper Large v3 | 
+|----------------------|:--------------:|:----------------:|
+| [AMI](https://huggingface.co/datasets/edinburghcstr/ami)                 | **8.72**       | 16.01            |    
+| [Earnings22](https://huggingface.co/datasets/revdotcom/earnings22)           | 12.37          | **11.3**        | 
+| [GigaSpeech](https://huggingface.co/datasets/speechcolab/gigaspeech)         | 10.27          | **10.02**        |     
+| [LibriSpeech clean](https://huggingface.co/datasets/openslr/librispeech_asr)   | **1.74**       | 2.03            |    
+| [LibriSpeech other](https://huggingface.co/datasets/openslr/librispeech_asr)   | 3.97           | **3.91**         |      
+| [SPGISpeech](https://huggingface.co/datasets/kensho/spgispeech)          | **2.71**           | 2.95        |     
+| [TED-LIUM](https://huggingface.co/datasets/LIUM/tedlium)             | **3.35**          | 3.9        |    
+| [VoxPopuli](https://huggingface.co/datasets/facebook/voxpopuli)           | **8.61**           | 9.52         |  
+| [CommonVoice](https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0)       | **8.19**           | 9.67        |      
+| **Average WER**      | **6.66**       | 7.7         |  
+
+#### Segmentation Performance
+
+CrisperWhisper demonstrates superior performance segmentation performance. This performance gap is especially pronounced around disfluencies and pauses.
+The following table uses the metrics as defined in the paper. For this table we used a collar of 50ms. Heads for each Model were selected using the method described in the [How](#5-how) section and the result attaining the highest F1 Score was choosen for each model using varying number of heads.
+
+| Dataset | Metric | CrisperWhisper | Whisper Large v2 | Whisper Large v3 |
+|---------|--------|------------------|------------------|------------------|
+| [AMI IHM](https://groups.inf.ed.ac.uk/ami/corpus/) | F1 Score | **0.79** | 0.63 | 0.66 |
+| | Avg IOU | **0.67** | 0.54 | 0.53 |
+| [Common Voice](https://commonvoice.mozilla.org/en/datasets) | F1 Score | **0.80** | 0.42 | 0.48 |
+| | Avg IOU | **0.70** | 0.32 | 0.43 |
+| [TIMIT](https://catalog.ldc.upenn.edu/LDC93S1) | F1 Score | **0.69** | 0.40 | 0.54 |
+| | Avg IOU | **0.56** | 0.32 | 0.43 |
+
+
+## 2. Usage 
+
+Here's how to use CrisperWhisper in your Python scripts:
+
+### 2.1 Usage with 🤗 transformers
+
+
+```python
+import os
+import sys
+import torch
+
+from datasets import load_dataset
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+
+def adjust_pauses_for_hf_pipeline_output(pipeline_output, split_threshold=0.12):
+    """
+    Adjust pause timings by distributing pauses up to the threshold evenly between adjacent words.
+    """
+
+    adjusted_chunks = pipeline_output["chunks"].copy()
+
+    for i in range(len(adjusted_chunks) - 1):
+        current_chunk = adjusted_chunks[i]
+        next_chunk = adjusted_chunks[i + 1]
+
+        current_start, current_end = current_chunk["timestamp"]
+        next_start, next_end = next_chunk["timestamp"]
+        pause_duration = next_start - current_end
+
+        if pause_duration > 0:
+            if pause_duration > split_threshold:
+                distribute = split_threshold / 2
+            else:
+                distribute = pause_duration / 2
+
+            # Adjust current chunk end time
+            adjusted_chunks[i]["timestamp"] = (current_start, current_end + distribute)
+
+            # Adjust next chunk start time
+            adjusted_chunks[i + 1]["timestamp"] = (next_start - distribute, next_end)
+    pipeline_output["chunks"] = adjusted_chunks
+
+    return pipeline_output
+
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+
+model_id = "nyrahealth/CrisperWhisper"
+
+model = AutoModelForSpeechSeq2Seq.from_pretrained(
+    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
+)
+model.to(device)
+
+processor = AutoProcessor.from_pretrained(model_id)
+
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model=model,
+    tokenizer=processor.tokenizer,
+    feature_extractor=processor.feature_extractor,
+    chunk_length_s=30,
+    batch_size=16,
+    return_timestamps='word',
+    torch_dtype=torch_dtype,
+    device=device,
+)
+
+dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
+sample = dataset[0]["audio"]
+hf_pipeline_output = pipe(sample)
+crisper_whisper_result = adjust_pauses_for_hf_pipeline_output(hf_pipeline_output)
+print(crisper_whisper_result)
+```
+
+read more about the reasoning behind the pause distribution logic in our paper.
+
+## 3. How?
+
+We employ the popular Dynamic Time Warping (DTW) on the Whisper cross-attention scores, as detailed in our [paper](https://arxiv.org/abs/2408.16589) to derive word-level timestamps. By leveraging our retokenization process, this method allows us to consistently detect pauses. Given that the accuracy of the timestamps heavily depends on the DTW cost matrix and, consequently, on the quality of the cross-attentions, we developed a specialized loss function for the selected alignment heads to enhance precision.
+
+Although this loss function was not included in the original [paper](https://arxiv.org/abs/2408.16589) due to time constraints preventing the completion of experiments and training before the submission deadline, it has been used to train our publicly available models.
+Key Features of this loss are as follows:
+
+1. **Data Preparation**
+    - We used datasets with word-level timestamp annotations, such as [AMI IHM](https://groups.inf.ed.ac.uk/ami/corpus/) and [TIMIT](https://catalog.ldc.upenn.edu/LDC93S1)   , but required additional timestamped data.
+    - To address this, we validated the alignment accuracy of several forced alignment tools using a small hand-labeled dataset.
+    - Based on this validation, we chose the [PyTorch CTC aligner](https://pytorch.org/audio/main/tutorials/ctc_forced_alignment_api_tutorial.html) to generate more time-aligned data from the CommonVoice dataset.
+    - Because the [PyTorch CTC aligner](https://pytorch.org/audio/main/tutorials/ctc_forced_alignment_api_tutorial.html) tends to overestimate pause durations, we applied the same pause-splitting method detailed in our [paper](...) to correct these errors. The effectiveness of this correction was confirmed using our hand-labeled dataset.
+
+2. **Token-Word Alignment**
+    - Due to retokenization as detailed in our [paper](https://arxiv.org/abs/2408.16589), each token is either part of a word or a pause/space, but never both
+    - Therefore each token can be cleanly aligned to a word OR a space/pause
+
+3. **Ground Truth Cross-Attention**
+    - We define the cross-attention ground truth for tokens as the L2-normalized vector, where:
+        - A value of 1 indicates that the word is active according to the word-level ground truth timestamp.
+        - A value of 0 indicates that no attention should be paid.
+    - To account for small inaccuracies in the ground truth timestamps, we apply a linear interpolation of 4 steps (8 milliseconds) on both sides of the ground truth vector, transitioning smoothly from 0 to 1.
+
+4. **Loss Calculation**
+- The loss function is defined as `1 - cosine similarity`  between the predicted cross-attention vector (when predicting a token) and the ground truth cross-attention vector.
+- This loss is averaged across all predicted tokens and alignment heads.
+
+5. **Alignment Head selection**
+- To choose the heads for alignment we evaluated the alignment performance of each individual decoder attention head on the timestamped timit dataset.
+- We choose the 15 best performing heads and finetune them using our attention loss.
+
+6. **Training Details**
+- Since most of our samples during training were shorter than 30 seconds we shift the audio sample and corresponding timestamp ground truth around with a 50% probability to mitigate the cross attentions ,,overfitting" to early positions of the encoder output.
+- If we have more than 40ms of silence (before or after shifting) we prepend the ground truth transcript ( and corresponding cross attention ground truth) with a space so the model has to accurately predict the starting time of the first word.
+- We use [WavLM](https://arxiv.org/abs/2110.13900) augmentations during Training adding random speech samples or noise to the audio wave to generally increase robustness of the transcription and stability of the alignment heads.
+- We clip ,,predicted" values in the cross attention vectors 4 seconds before and 4 seconds after the groundtruth word they belong to to 0. This is to decrease the dimensionality of the cross attention vector and therefore emphasize the attention where it counts in the loss and ultimately for the alignment.
+- With a probability of 1% we use samples containing exclusively noise where the model has to return a empty prediction to improve hallucination.
+- The Model is trained on a mixture of english and german datasets so we only gurantee good performance on these languages
+- The Model is trained in three stages, in the first stage we use around 10000 hours of audio to adjust Whisper to the new tokenizer. In the second stage we exclusively use high quality datasets that are transcribed in a verbatim fashion. Finally we continue training on this verbatim mixture and add the attention loss for another 6000 steps.
+
+
+## License
+---
+license: cc-by-nc-4.0
+---

added_tokens.json

@@ -0,0 +1,1611 @@
+{
+  "<|0.00|>": 50365,
+  "<|0.02|>": 50366,
+  "<|0.04|>": 50367,
+  "<|0.06|>": 50368,
+  "<|0.08|>": 50369,
+  "<|0.10|>": 50370,
+  "<|0.12|>": 50371,
+  "<|0.14|>": 50372,
+  "<|0.16|>": 50373,
+  "<|0.18|>": 50374,
+  "<|0.20|>": 50375,
+  "<|0.22|>": 50376,
+  "<|0.24|>": 50377,
+  "<|0.26|>": 50378,
+  "<|0.28|>": 50379,
+  "<|0.30|>": 50380,
+  "<|0.32|>": 50381,
+  "<|0.34|>": 50382,
+  "<|0.36|>": 50383,
+  "<|0.38|>": 50384,
+  "<|0.40|>": 50385,
+  "<|0.42|>": 50386,
+  "<|0.44|>": 50387,
+  "<|0.46|>": 50388,
+  "<|0.48|>": 50389,
+  "<|0.50|>": 50390,
+  "<|0.52|>": 50391,
+  "<|0.54|>": 50392,
+  "<|0.56|>": 50393,
+  "<|0.58|>": 50394,
+  "<|0.60|>": 50395,
+  "<|0.62|>": 50396,
+  "<|0.64|>": 50397,
+  "<|0.66|>": 50398,
+  "<|0.68|>": 50399,
+  "<|0.70|>": 50400,
+  "<|0.72|>": 50401,
+  "<|0.74|>": 50402,
+  "<|0.76|>": 50403,
+  "<|0.78|>": 50404,
+  "<|0.80|>": 50405,
+  "<|0.82|>": 50406,
+  "<|0.84|>": 50407,
+  "<|0.86|>": 50408,
+  "<|0.88|>": 50409,
+  "<|0.90|>": 50410,
+  "<|0.92|>": 50411,
+  "<|0.94|>": 50412,
+  "<|0.96|>": 50413,
+  "<|0.98|>": 50414,
+  "<|1.00|>": 50415,
+  "<|1.02|>": 50416,
+  "<|1.04|>": 50417,
+  "<|1.06|>": 50418,
+  "<|1.08|>": 50419,
+  "<|1.10|>": 50420,
+  "<|1.12|>": 50421,
+  "<|1.14|>": 50422,
+  "<|1.16|>": 50423,
+  "<|1.18|>": 50424,
+  "<|1.20|>": 50425,
+  "<|1.22|>": 50426,
+  "<|1.24|>": 50427,
+  "<|1.26|>": 50428,
+  "<|1.28|>": 50429,
+  "<|1.30|>": 50430,
+  "<|1.32|>": 50431,
+  "<|1.34|>": 50432,
+  "<|1.36|>": 50433,
+  "<|1.38|>": 50434,
+  "<|1.40|>": 50435,
+  "<|1.42|>": 50436,
+  "<|1.44|>": 50437,
+  "<|1.46|>": 50438,
+  "<|1.48|>": 50439,
+  "<|1.50|>": 50440,
+  "<|1.52|>": 50441,
+  "<|1.54|>": 50442,
+  "<|1.56|>": 50443,
+  "<|1.58|>": 50444,
+  "<|1.60|>": 50445,
+  "<|1.62|>": 50446,
+  "<|1.64|>": 50447,
+  "<|1.66|>": 50448,
+  "<|1.68|>": 50449,
+  "<|1.70|>": 50450,
+  "<|1.72|>": 50451,
+  "<|1.74|>": 50452,
+  "<|1.76|>": 50453,
+  "<|1.78|>": 50454,
+  "<|1.80|>": 50455,
+  "<|1.82|>": 50456,
+  "<|1.84|>": 50457,
+  "<|1.86|>": 50458,
+  "<|1.88|>": 50459,
+  "<|1.90|>": 50460,
+  "<|1.92|>": 50461,
+  "<|1.94|>": 50462,
+  "<|1.96|>": 50463,
+  "<|1.98|>": 50464,
+  "<|10.00|>": 50865,
+  "<|10.02|>": 50866,
+  "<|10.04|>": 50867,
+  "<|10.06|>": 50868,
+  "<|10.08|>": 50869,
+  "<|10.10|>": 50870,
+  "<|10.12|>": 50871,
+  "<|10.14|>": 50872,
+  "<|10.16|>": 50873,
+  "<|10.18|>": 50874,
+  "<|10.20|>": 50875,
+  "<|10.22|>": 50876,
+  "<|10.24|>": 50877,
+  "<|10.26|>": 50878,
+  "<|10.28|>": 50879,
+  "<|10.30|>": 50880,
+  "<|10.32|>": 50881,
+  "<|10.34|>": 50882,
+  "<|10.36|>": 50883,
+  "<|10.38|>": 50884,
+  "<|10.40|>": 50885,
+  "<|10.42|>": 50886,
+  "<|10.44|>": 50887,
+  "<|10.46|>": 50888,
+  "<|10.48|>": 50889,
+  "<|10.50|>": 50890,
+  "<|10.52|>": 50891,
+  "<|10.54|>": 50892,
+  "<|10.56|>": 50893,
+  "<|10.58|>": 50894,
+  "<|10.60|>": 50895,
+  "<|10.62|>": 50896,
+  "<|10.64|>": 50897,
+  "<|10.66|>": 50898,
+  "<|10.68|>": 50899,
+  "<|10.70|>": 50900,
+  "<|10.72|>": 50901,
+  "<|10.74|>": 50902,
+  "<|10.76|>": 50903,
+  "<|10.78|>": 50904,
+  "<|10.80|>": 50905,
+  "<|10.82|>": 50906,
+  "<|10.84|>": 50907,
+  "<|10.86|>": 50908,
+  "<|10.88|>": 50909,
+  "<|10.90|>": 50910,
+  "<|10.92|>": 50911,
+  "<|10.94|>": 50912,
+  "<|10.96|>": 50913,
+  "<|10.98|>": 50914,
+  "<|11.00|>": 50915,
+  "<|11.02|>": 50916,
+  "<|11.04|>": 50917,
+  "<|11.06|>": 50918,
+  "<|11.08|>": 50919,
+  "<|11.10|>": 50920,
+  "<|11.12|>": 50921,
+  "<|11.14|>": 50922,
+  "<|11.16|>": 50923,
+  "<|11.18|>": 50924,
+  "<|11.20|>": 50925,
+  "<|11.22|>": 50926,
+  "<|11.24|>": 50927,
+  "<|11.26|>": 50928,
+  "<|11.28|>": 50929,
+  "<|11.30|>": 50930,
+  "<|11.32|>": 50931,
+  "<|11.34|>": 50932,
+  "<|11.36|>": 50933,
+  "<|11.38|>": 50934,
+  "<|11.40|>": 50935,
+  "<|11.42|>": 50936,
+  "<|11.44|>": 50937,
+  "<|11.46|>": 50938,
+  "<|11.48|>": 50939,
+  "<|11.50|>": 50940,
+  "<|11.52|>": 50941,
+  "<|11.54|>": 50942,
+  "<|11.56|>": 50943,
+  "<|11.58|>": 50944,
+  "<|11.60|>": 50945,
+  "<|11.62|>": 50946,
+  "<|11.64|>": 50947,
+  "<|11.66|>": 50948,
+  "<|11.68|>": 50949,
+  "<|11.70|>": 50950,
+  "<|11.72|>": 50951,
+  "<|11.74|>": 50952,
+  "<|11.76|>": 50953,
+  "<|11.78|>": 50954,
+  "<|11.80|>": 50955,
+  "<|11.82|>": 50956,
+  "<|11.84|>": 50957,
+  "<|11.86|>": 50958,
+  "<|11.88|>": 50959,
+  "<|11.90|>": 50960,
+  "<|11.92|>": 50961,
+  "<|11.94|>": 50962,
+  "<|11.96|>": 50963,
+  "<|11.98|>": 50964,
+  "<|12.00|>": 50965,
+  "<|12.02|>": 50966,
+  "<|12.04|>": 50967,
+  "<|12.06|>": 50968,
+  "<|12.08|>": 50969,
+  "<|12.10|>": 50970,
+  "<|12.12|>": 50971,
+  "<|12.14|>": 50972,
+  "<|12.16|>": 50973,
+  "<|12.18|>": 50974,
+  "<|12.20|>": 50975,
+  "<|12.22|>": 50976,
+  "<|12.24|>": 50977,
+  "<|12.26|>": 50978,
+  "<|12.28|>": 50979,
+  "<|12.30|>": 50980,
+  "<|12.32|>": 50981,
+  "<|12.34|>": 50982,
+  "<|12.36|>": 50983,
+  "<|12.38|>": 50984,
+  "<|12.40|>": 50985,
+  "<|12.42|>": 50986,
+  "<|12.44|>": 50987,
+  "<|12.46|>": 50988,
+  "<|12.48|>": 50989,
+  "<|12.50|>": 50990,
+  "<|12.52|>": 50991,
+  "<|12.54|>": 50992,
+  "<|12.56|>": 50993,
+  "<|12.58|>": 50994,
+  "<|12.60|>": 50995,
+  "<|12.62|>": 50996,
+  "<|12.64|>": 50997,
+  "<|12.66|>": 50998,
+  "<|12.68|>": 50999,
+  "<|12.70|>": 51000,
+  "<|12.72|>": 51001,
+  "<|12.74|>": 51002,
+  "<|12.76|>": 51003,
+  "<|12.78|>": 51004,
+  "<|12.80|>": 51005,
+  "<|12.82|>": 51006,
+  "<|12.84|>": 51007,
+  "<|12.86|>": 51008,
+  "<|12.88|>": 51009,
+  "<|12.90|>": 51010,
+  "<|12.92|>": 51011,
+  "<|12.94|>": 51012,
+  "<|12.96|>": 51013,
+  "<|12.98|>": 51014,
+  "<|13.00|>": 51015,
+  "<|13.02|>": 51016,
+  "<|13.04|>": 51017,
+  "<|13.06|>": 51018,
+  "<|13.08|>": 51019,
+  "<|13.10|>": 51020,
+  "<|13.12|>": 51021,
+  "<|13.14|>": 51022,
+  "<|13.16|>": 51023,
+  "<|13.18|>": 51024,
+  "<|13.20|>": 51025,
+  "<|13.22|>": 51026,
+  "<|13.24|>": 51027,
+  "<|13.26|>": 51028,
+  "<|13.28|>": 51029,
+  "<|13.30|>": 51030,
+  "<|13.32|>": 51031,
+  "<|13.34|>": 51032,
+  "<|13.36|>": 51033,
+  "<|13.38|>": 51034,
+  "<|13.40|>": 51035,
+  "<|13.42|>": 51036,
+  "<|13.44|>": 51037,
+  "<|13.46|>": 51038,
+  "<|13.48|>": 51039,
+  "<|13.50|>": 51040,
+  "<|13.52|>": 51041,
+  "<|13.54|>": 51042,
+  "<|13.56|>": 51043,
+  "<|13.58|>": 51044,
+  "<|13.60|>": 51045,
+  "<|13.62|>": 51046,
+  "<|13.64|>": 51047,
+  "<|13.66|>": 51048,
+  "<|13.68|>": 51049,
+  "<|13.70|>": 51050,
+  "<|13.72|>": 51051,
+  "<|13.74|>": 51052,
+  "<|13.76|>": 51053,
+  "<|13.78|>": 51054,
+  "<|13.80|>": 51055,
+  "<|13.82|>": 51056,
+  "<|13.84|>": 51057,
+  "<|13.86|>": 51058,
+  "<|13.88|>": 51059,
+  "<|13.90|>": 51060,
+  "<|13.92|>": 51061,
+  "<|13.94|>": 51062,
+  "<|13.96|>": 51063,
+  "<|13.98|>": 51064,
+  "<|14.00|>": 51065,
+  "<|14.02|>": 51066,
+  "<|14.04|>": 51067,
+  "<|14.06|>": 51068,
+  "<|14.08|>": 51069,
+  "<|14.10|>": 51070,
+  "<|14.12|>": 51071,
+  "<|14.14|>": 51072,
+  "<|14.16|>": 51073,
+  "<|14.18|>": 51074,
+  "<|14.20|>": 51075,
+  "<|14.22|>": 51076,
+  "<|14.24|>": 51077,
+  "<|14.26|>": 51078,
+  "<|14.28|>": 51079,
+  "<|14.30|>": 51080,
+  "<|14.32|>": 51081,
+  "<|14.34|>": 51082,
+  "<|14.36|>": 51083,
+  "<|14.38|>": 51084,
+  "<|14.40|>": 51085,
+  "<|14.42|>": 51086,
+  "<|14.44|>": 51087,
+  "<|14.46|>": 51088,
+  "<|14.48|>": 51089,
+  "<|14.50|>": 51090,
+  "<|14.52|>": 51091,
+  "<|14.54|>": 51092,
+  "<|14.56|>": 51093,
+  "<|14.58|>": 51094,
+  "<|14.60|>": 51095,
+  "<|14.62|>": 51096,
+  "<|14.64|>": 51097,
+  "<|14.66|>": 51098,
+  "<|14.68|>": 51099,
+  "<|14.70|>": 51100,
+  "<|14.72|>": 51101,
+  "<|14.74|>": 51102,
+  "<|14.76|>": 51103,
+  "<|14.78|>": 51104,
+  "<|14.80|>": 51105,
+  "<|14.82|>": 51106,
+  "<|14.84|>": 51107,
+  "<|14.86|>": 51108,
+  "<|14.88|>": 51109,
+  "<|14.90|>": 51110,
+  "<|14.92|>": 51111,
+  "<|14.94|>": 51112,
+  "<|14.96|>": 51113,
+  "<|14.98|>": 51114,
+  "<|15.00|>": 51115,
+  "<|15.02|>": 51116,
+  "<|15.04|>": 51117,
+  "<|15.06|>": 51118,
+  "<|15.08|>": 51119,
+  "<|15.10|>": 51120,
+  "<|15.12|>": 51121,
+  "<|15.14|>": 51122,
+  "<|15.16|>": 51123,
+  "<|15.18|>": 51124,
+  "<|15.20|>": 51125,
+  "<|15.22|>": 51126,
+  "<|15.24|>": 51127,
+  "<|15.26|>": 51128,
+  "<|15.28|>": 51129,
+  "<|15.30|>": 51130,
+  "<|15.32|>": 51131,
+  "<|15.34|>": 51132,
+  "<|15.36|>": 51133,
+  "<|15.38|>": 51134,
+  "<|15.40|>": 51135,
+  "<|15.42|>": 51136,
+  "<|15.44|>": 51137,
+  "<|15.46|>": 51138,
+  "<|15.48|>": 51139,
+  "<|15.50|>": 51140,
+  "<|15.52|>": 51141,
+  "<|15.54|>": 51142,
+  "<|15.56|>": 51143,
+  "<|15.58|>": 51144,
+  "<|15.60|>": 51145,
+  "<|15.62|>": 51146,
+  "<|15.64|>": 51147,
+  "<|15.66|>": 51148,
+  "<|15.68|>": 51149,
+  "<|15.70|>": 51150,
+  "<|15.72|>": 51151,
+  "<|15.74|>": 51152,
+  "<|15.76|>": 51153,
+  "<|15.78|>": 51154,
+  "<|15.80|>": 51155,
+  "<|15.82|>": 51156,
+  "<|15.84|>": 51157,
+  "<|15.86|>": 51158,
+  "<|15.88|>": 51159,
+  "<|15.90|>": 51160,
+  "<|15.92|>": 51161,
+  "<|15.94|>": 51162,
+  "<|15.96|>": 51163,
+  "<|15.98|>": 51164,
+  "<|16.00|>": 51165,
+  "<|16.02|>": 51166,
+  "<|16.04|>": 51167,
+  "<|16.06|>": 51168,
+  "<|16.08|>": 51169,
+  "<|16.10|>": 51170,
+  "<|16.12|>": 51171,
+  "<|16.14|>": 51172,
+  "<|16.16|>": 51173,
+  "<|16.18|>": 51174,
+  "<|16.20|>": 51175,
+  "<|16.22|>": 51176,
+  "<|16.24|>": 51177,
+  "<|16.26|>": 51178,
+  "<|16.28|>": 51179,
+  "<|16.30|>": 51180,
+  "<|16.32|>": 51181,
+  "<|16.34|>": 51182,
+  "<|16.36|>": 51183,
+  "<|16.38|>": 51184,
+  "<|16.40|>": 51185,
+  "<|16.42|>": 51186,
+  "<|16.44|>": 51187,
+  "<|16.46|>": 51188,
+  "<|16.48|>": 51189,
+  "<|16.50|>": 51190,
+  "<|16.52|>": 51191,
+  "<|16.54|>": 51192,
+  "<|16.56|>": 51193,
+  "<|16.58|>": 51194,
+  "<|16.60|>": 51195,
+  "<|16.62|>": 51196,
+  "<|16.64|>": 51197,
+  "<|16.66|>": 51198,
+  "<|16.68|>": 51199,
+  "<|16.70|>": 51200,
+  "<|16.72|>": 51201,
+  "<|16.74|>": 51202,
+  "<|16.76|>": 51203,
+  "<|16.78|>": 51204,
+  "<|16.80|>": 51205,
+  "<|16.82|>": 51206,
+  "<|16.84|>": 51207,
+  "<|16.86|>": 51208,
+  "<|16.88|>": 51209,
+  "<|16.90|>": 51210,
+  "<|16.92|>": 51211,
+  "<|16.94|>": 51212,
+  "<|16.96|>": 51213,
+  "<|16.98|>": 51214,
+  "<|17.00|>": 51215,
+  "<|17.02|>": 51216,
+  "<|17.04|>": 51217,
+  "<|17.06|>": 51218,
+  "<|17.08|>": 51219,
+  "<|17.10|>": 51220,
+  "<|17.12|>": 51221,
+  "<|17.14|>": 51222,
+  "<|17.16|>": 51223,
+  "<|17.18|>": 51224,
+  "<|17.20|>": 51225,
+  "<|17.22|>": 51226,
+  "<|17.24|>": 51227,
+  "<|17.26|>": 51228,
+  "<|17.28|>": 51229,
+  "<|17.30|>": 51230,
+  "<|17.32|>": 51231,
+  "<|17.34|>": 51232,
+  "<|17.36|>": 51233,
+  "<|17.38|>": 51234,
+  "<|17.40|>": 51235,
+  "<|17.42|>": 51236,
+  "<|17.44|>": 51237,
+  "<|17.46|>": 51238,
+  "<|17.48|>": 51239,
+  "<|17.50|>": 51240,
+  "<|17.52|>": 51241,
+  "<|17.54|>": 51242,
+  "<|17.56|>": 51243,
+  "<|17.58|>": 51244,
+  "<|17.60|>": 51245,
+  "<|17.62|>": 51246,
+  "<|17.64|>": 51247,
+  "<|17.66|>": 51248,
+  "<|17.68|>": 51249,
+  "<|17.70|>": 51250,
+  "<|17.72|>": 51251,
+  "<|17.74|>": 51252,
+  "<|17.76|>": 51253,
+  "<|17.78|>": 51254,
+  "<|17.80|>": 51255,
+  "<|17.82|>": 51256,
+  "<|17.84|>": 51257,
+  "<|17.86|>": 51258,
+  "<|17.88|>": 51259,
+  "<|17.90|>": 51260,
+  "<|17.92|>": 51261,
+  "<|17.94|>": 51262,
+  "<|17.96|>": 51263,
+  "<|17.98|>": 51264,
+  "<|18.00|>": 51265,
+  "<|18.02|>": 51266,
+  "<|18.04|>": 51267,
+  "<|18.06|>": 51268,
+  "<|18.08|>": 51269,
+  "<|18.10|>": 51270,
+  "<|18.12|>": 51271,
+  "<|18.14|>": 51272,
+  "<|18.16|>": 51273,
+  "<|18.18|>": 51274,
+  "<|18.20|>": 51275,
+  "<|18.22|>": 51276,
+  "<|18.24|>": 51277,
+  "<|18.26|>": 51278,
+  "<|18.28|>": 51279,
+  "<|18.30|>": 51280,
+  "<|18.32|>": 51281,
+  "<|18.34|>": 51282,
+  "<|18.36|>": 51283,
+  "<|18.38|>": 51284,
+  "<|18.40|>": 51285,
+  "<|18.42|>": 51286,
+  "<|18.44|>": 51287,
+  "<|18.46|>": 51288,
+  "<|18.48|>": 51289,
+  "<|18.50|>": 51290,
+  "<|18.52|>": 51291,
+  "<|18.54|>": 51292,
+  "<|18.56|>": 51293,
+  "<|18.58|>": 51294,
+  "<|18.60|>": 51295,
+  "<|18.62|>": 51296,
+  "<|18.64|>": 51297,
+  "<|18.66|>": 51298,
+  "<|18.68|>": 51299,
+  "<|18.70|>": 51300,
+  "<|18.72|>": 51301,
+  "<|18.74|>": 51302,
+  "<|18.76|>": 51303,
+  "<|18.78|>": 51304,
+  "<|18.80|>": 51305,
+  "<|18.82|>": 51306,
+  "<|18.84|>": 51307,
+  "<|18.86|>": 51308,
+  "<|18.88|>": 51309,
+  "<|18.90|>": 51310,
+  "<|18.92|>": 51311,
+  "<|18.94|>": 51312,
+  "<|18.96|>": 51313,
+  "<|18.98|>": 51314,
+  "<|19.00|>": 51315,
+  "<|19.02|>": 51316,
+  "<|19.04|>": 51317,
+  "<|19.06|>": 51318,
+  "<|19.08|>": 51319,
+  "<|19.10|>": 51320,
+  "<|19.12|>": 51321,
+  "<|19.14|>": 51322,
+  "<|19.16|>": 51323,
+  "<|19.18|>": 51324,
+  "<|19.20|>": 51325,
+  "<|19.22|>": 51326,
+  "<|19.24|>": 51327,
+  "<|19.26|>": 51328,
+  "<|19.28|>": 51329,
+  "<|19.30|>": 51330,
+  "<|19.32|>": 51331,
+  "<|19.34|>": 51332,
+  "<|19.36|>": 51333,
+  "<|19.38|>": 51334,
+  "<|19.40|>": 51335,
+  "<|19.42|>": 51336,
+  "<|19.44|>": 51337,
+  "<|19.46|>": 51338,
+  "<|19.48|>": 51339,
+  "<|19.50|>": 51340,
+  "<|19.52|>": 51341,
+  "<|19.54|>": 51342,
+  "<|19.56|>": 51343,
+  "<|19.58|>": 51344,
+  "<|19.60|>": 51345,
+  "<|19.62|>": 51346,
+  "<|19.64|>": 51347,
+  "<|19.66|>": 51348,
+  "<|19.68|>": 51349,
+  "<|19.70|>": 51350,
+  "<|19.72|>": 51351,
+  "<|19.74|>": 51352,
+  "<|19.76|>": 51353,
+  "<|19.78|>": 51354,
+  "<|19.80|>": 51355,
+  "<|19.82|>": 51356,
+  "<|19.84|>": 51357,
+  "<|19.86|>": 51358,
+  "<|19.88|>": 51359,
+  "<|19.90|>": 51360,
+  "<|19.92|>": 51361,
+  "<|19.94|>": 51362,
+  "<|19.96|>": 51363,
+  "<|19.98|>": 51364,
+  "<|2.00|>": 50465,
+  "<|2.02|>": 50466,
+  "<|2.04|>": 50467,
+  "<|2.06|>": 50468,
+  "<|2.08|>": 50469,
+  "<|2.10|>": 50470,
+  "<|2.12|>": 50471,
+  "<|2.14|>": 50472,
+  "<|2.16|>": 50473,
+  "<|2.18|>": 50474,
+  "<|2.20|>": 50475,
+  "<|2.22|>": 50476,
+  "<|2.24|>": 50477,
+  "<|2.26|>": 50478,
+  "<|2.28|>": 50479,
+  "<|2.30|>": 50480,
+  "<|2.32|>": 50481,
+  "<|2.34|>": 50482,
+  "<|2.36|>": 50483,
+  "<|2.38|>": 50484,
+  "<|2.40|>": 50485,
+  "<|2.42|>": 50486,
+  "<|2.44|>": 50487,
+  "<|2.46|>": 50488,
+  "<|2.48|>": 50489,
+  "<|2.50|>": 50490,
+  "<|2.52|>": 50491,
+  "<|2.54|>": 50492,
+  "<|2.56|>": 50493,
+  "<|2.58|>": 50494,
+  "<|2.60|>": 50495,
+  "<|2.62|>": 50496,
+  "<|2.64|>": 50497,
+  "<|2.66|>": 50498,
+  "<|2.68|>": 50499,
+  "<|2.70|>": 50500,
+  "<|2.72|>": 50501,
+  "<|2.74|>": 50502,
+  "<|2.76|>": 50503,
+  "<|2.78|>": 50504,
+  "<|2.80|>": 50505,
+  "<|2.82|>": 50506,
+  "<|2.84|>": 50507,
+  "<|2.86|>": 50508,
+  "<|2.88|>": 50509,
+  "<|2.90|>": 50510,
+  "<|2.92|>": 50511,
+  "<|2.94|>": 50512,
+  "<|2.96|>": 50513,
+  "<|2.98|>": 50514,
+  "<|20.00|>": 51365,
+  "<|20.02|>": 51366,
+  "<|20.04|>": 51367,
+  "<|20.06|>": 51368,
+  "<|20.08|>": 51369,
+  "<|20.10|>": 51370,
+  "<|20.12|>": 51371,
+  "<|20.14|>": 51372,
+  "<|20.16|>": 51373,
+  "<|20.18|>": 51374,
+  "<|20.20|>": 51375,
+  "<|20.22|>": 51376,
+  "<|20.24|>": 51377,
+  "<|20.26|>": 51378,
+  "<|20.28|>": 51379,
+  "<|20.30|>": 51380,
+  "<|20.32|>": 51381,
+  "<|20.34|>": 51382,
+  "<|20.36|>": 51383,
+  "<|20.38|>": 51384,
+  "<|20.40|>": 51385,
+  "<|20.42|>": 51386,
+  "<|20.44|>": 51387,
+  "<|20.46|>": 51388,
+  "<|20.48|>": 51389,
+  "<|20.50|>": 51390,
+  "<|20.52|>": 51391,
+  "<|20.54|>": 51392,
+  "<|20.56|>": 51393,
+  "<|20.58|>": 51394,
+  "<|20.60|>": 51395,
+  "<|20.62|>": 51396,
+  "<|20.64|>": 51397,
+  "<|20.66|>": 51398,
+  "<|20.68|>": 51399,
+  "<|20.70|>": 51400,
+  "<|20.72|>": 51401,
+  "<|20.74|>": 51402,
+  "<|20.76|>": 51403,
+  "<|20.78|>": 51404,
+  "<|20.80|>": 51405,
+  "<|20.82|>": 51406,
+  "<|20.84|>": 51407,
+  "<|20.86|>": 51408,
+  "<|20.88|>": 51409,
+  "<|20.90|>": 51410,
+  "<|20.92|>": 51411,
+  "<|20.94|>": 51412,
+  "<|20.96|>": 51413,
+  "<|20.98|>": 51414,
+  "<|21.00|>": 51415,
+  "<|21.02|>": 51416,
+  "<|21.04|>": 51417,
+  "<|21.06|>": 51418,
+  "<|21.08|>": 51419,
+  "<|21.10|>": 51420,
+  "<|21.12|>": 51421,
+  "<|21.14|>": 51422,
+  "<|21.16|>": 51423,
+  "<|21.18|>": 51424,
+  "<|21.20|>": 51425,
+  "<|21.22|>": 51426,
+  "<|21.24|>": 51427,
+  "<|21.26|>": 51428,
+  "<|21.28|>": 51429,
+  "<|21.30|>": 51430,
+  "<|21.32|>": 51431,
+  "<|21.34|>": 51432,
+  "<|21.36|>": 51433,
+  "<|21.38|>": 51434,
+  "<|21.40|>": 51435,
+  "<|21.42|>": 51436,
+  "<|21.44|>": 51437,
+  "<|21.46|>": 51438,
+  "<|21.48|>": 51439,
+  "<|21.50|>": 51440,
+  "<|21.52|>": 51441,
+  "<|21.54|>": 51442,
+  "<|21.56|>": 51443,
+  "<|21.58|>": 51444,
+  "<|21.60|>": 51445,
+  "<|21.62|>": 51446,
+  "<|21.64|>": 51447,
+  "<|21.66|>": 51448,
+  "<|21.68|>": 51449,
+  "<|21.70|>": 51450,
+  "<|21.72|>": 51451,
+  "<|21.74|>": 51452,
+  "<|21.76|>": 51453,
+  "<|21.78|>": 51454,
+  "<|21.80|>": 51455,
+  "<|21.82|>": 51456,
+  "<|21.84|>": 51457,
+  "<|21.86|>": 51458,
+  "<|21.88|>": 51459,
+  "<|21.90|>": 51460,
+  "<|21.92|>": 51461,
+  "<|21.94|>": 51462,
+  "<|21.96|>": 51463,
+  "<|21.98|>": 51464,
+  "<|22.00|>": 51465,
+  "<|22.02|>": 51466,
+  "<|22.04|>": 51467,
+  "<|22.06|>": 51468,
+  "<|22.08|>": 51469,
+  "<|22.10|>": 51470,
+  "<|22.12|>": 51471,
+  "<|22.14|>": 51472,
+  "<|22.16|>": 51473,
+  "<|22.18|>": 51474,
+  "<|22.20|>": 51475,
+  "<|22.22|>": 51476,
+  "<|22.24|>": 51477,
+  "<|22.26|>": 51478,
+  "<|22.28|>": 51479,
+  "<|22.30|>": 51480,
+  "<|22.32|>": 51481,
+  "<|22.34|>": 51482,
+  "<|22.36|>": 51483,
+  "<|22.38|>": 51484,
+  "<|22.40|>": 51485,
+  "<|22.42|>": 51486,
+  "<|22.44|>": 51487,
+  "<|22.46|>": 51488,
+  "<|22.48|>": 51489,
+  "<|22.50|>": 51490,
+  "<|22.52|>": 51491,
+  "<|22.54|>": 51492,
+  "<|22.56|>": 51493,
+  "<|22.58|>": 51494,
+  "<|22.60|>": 51495,
+  "<|22.62|>": 51496,
+  "<|22.64|>": 51497,
+  "<|22.66|>": 51498,
+  "<|22.68|>": 51499,
+  "<|22.70|>": 51500,
+  "<|22.72|>": 51501,
+  "<|22.74|>": 51502,
+  "<|22.76|>": 51503,
+  "<|22.78|>": 51504,
+  "<|22.80|>": 51505,
+  "<|22.82|>": 51506,
+  "<|22.84|>": 51507,
+  "<|22.86|>": 51508,
+  "<|22.88|>": 51509,
+  "<|22.90|>": 51510,
+  "<|22.92|>": 51511,
+  "<|22.94|>": 51512,
+  "<|22.96|>": 51513,
+  "<|22.98|>": 51514,
+  "<|23.00|>": 51515,
+  "<|23.02|>": 51516,
+  "<|23.04|>": 51517,
+  "<|23.06|>": 51518,
+  "<|23.08|>": 51519,
+  "<|23.10|>": 51520,
+  "<|23.12|>": 51521,
+  "<|23.14|>": 51522,
+  "<|23.16|>": 51523,
+  "<|23.18|>": 51524,
+  "<|23.20|>": 51525,
+  "<|23.22|>": 51526,
+  "<|23.24|>": 51527,
+  "<|23.26|>": 51528,
+  "<|23.28|>": 51529,
+  "<|23.30|>": 51530,
+  "<|23.32|>": 51531,
+  "<|23.34|>": 51532,
+  "<|23.36|>": 51533,
+  "<|23.38|>": 51534,
+  "<|23.40|>": 51535,
+  "<|23.42|>": 51536,
+  "<|23.44|>": 51537,
+  "<|23.46|>": 51538,
+  "<|23.48|>": 51539,
+  "<|23.50|>": 51540,
+  "<|23.52|>": 51541,
+  "<|23.54|>": 51542,
+  "<|23.56|>": 51543,
+  "<|23.58|>": 51544,
+  "<|23.60|>": 51545,
+  "<|23.62|>": 51546,
+  "<|23.64|>": 51547,
+  "<|23.66|>": 51548,
+  "<|23.68|>": 51549,
+  "<|23.70|>": 51550,
+  "<|23.72|>": 51551,
+  "<|23.74|>": 51552,
+  "<|23.76|>": 51553,
+  "<|23.78|>": 51554,
+  "<|23.80|>": 51555,
+  "<|23.82|>": 51556,
+  "<|23.84|>": 51557,
+  "<|23.86|>": 51558,
+  "<|23.88|>": 51559,
+  "<|23.90|>": 51560,
+  "<|23.92|>": 51561,
+  "<|23.94|>": 51562,
+  "<|23.96|>": 51563,
+  "<|23.98|>": 51564,
+  "<|24.00|>": 51565,
+  "<|24.02|>": 51566,
+  "<|24.04|>": 51567,
+  "<|24.06|>": 51568,
+  "<|24.08|>": 51569,
+  "<|24.10|>": 51570,
+  "<|24.12|>": 51571,
+  "<|24.14|>": 51572,
+  "<|24.16|>": 51573,
+  "<|24.18|>": 51574,
+  "<|24.20|>": 51575,
+  "<|24.22|>": 51576,
+  "<|24.24|>": 51577,
+  "<|24.26|>": 51578,
+  "<|24.28|>": 51579,
+  "<|24.30|>": 51580,
+  "<|24.32|>": 51581,
+  "<|24.34|>": 51582,
+  "<|24.36|>": 51583,
+  "<|24.38|>": 51584,
+  "<|24.40|>": 51585,
+  "<|24.42|>": 51586,
+  "<|24.44|>": 51587,
+  "<|24.46|>": 51588,
+  "<|24.48|>": 51589,
+  "<|24.50|>": 51590,
+  "<|24.52|>": 51591,
+  "<|24.54|>": 51592,
+  "<|24.56|>": 51593,
+  "<|24.58|>": 51594,
+  "<|24.60|>": 51595,
+  "<|24.62|>": 51596,
+  "<|24.64|>": 51597,
+  "<|24.66|>": 51598,
+  "<|24.68|>": 51599,
+  "<|24.70|>": 51600,
+  "<|24.72|>": 51601,
+  "<|24.74|>": 51602,
+  "<|24.76|>": 51603,
+  "<|24.78|>": 51604,
+  "<|24.80|>": 51605,
+  "<|24.82|>": 51606,
+  "<|24.84|>": 51607,
+  "<|24.86|>": 51608,
+  "<|24.88|>": 51609,
+  "<|24.90|>": 51610,
+  "<|24.92|>": 51611,
+  "<|24.94|>": 51612,
+  "<|24.96|>": 51613,
+  "<|24.98|>": 51614,
+  "<|25.00|>": 51615,
+  "<|25.02|>": 51616,
+  "<|25.04|>": 51617,
+  "<|25.06|>": 51618,
+  "<|25.08|>": 51619,
+  "<|25.10|>": 51620,
+  "<|25.12|>": 51621,
+  "<|25.14|>": 51622,
+  "<|25.16|>": 51623,
+  "<|25.18|>": 51624,
+  "<|25.20|>": 51625,
+  "<|25.22|>": 51626,
+  "<|25.24|>": 51627,
+  "<|25.26|>": 51628,
+  "<|25.28|>": 51629,
+  "<|25.30|>": 51630,
+  "<|25.32|>": 51631,
+  "<|25.34|>": 51632,
+  "<|25.36|>": 51633,
+  "<|25.38|>": 51634,
+  "<|25.40|>": 51635,
+  "<|25.42|>": 51636,
+  "<|25.44|>": 51637,
+  "<|25.46|>": 51638,
+  "<|25.48|>": 51639,
+  "<|25.50|>": 51640,
+  "<|25.52|>": 51641,
+  "<|25.54|>": 51642,
+  "<|25.56|>": 51643,
+  "<|25.58|>": 51644,
+  "<|25.60|>": 51645,
+  "<|25.62|>": 51646,
+  "<|25.64|>": 51647,
+  "<|25.66|>": 51648,
+  "<|25.68|>": 51649,
+  "<|25.70|>": 51650,
+  "<|25.72|>": 51651,
+  "<|25.74|>": 51652,
+  "<|25.76|>": 51653,
+  "<|25.78|>": 51654,
+  "<|25.80|>": 51655,
+  "<|25.82|>": 51656,
+  "<|25.84|>": 51657,
+  "<|25.86|>": 51658,
+  "<|25.88|>": 51659,
+  "<|25.90|>": 51660,
+  "<|25.92|>": 51661,
+  "<|25.94|>": 51662,
+  "<|25.96|>": 51663,
+  "<|25.98|>": 51664,
+  "<|26.00|>": 51665,
+  "<|26.02|>": 51666,
+  "<|26.04|>": 51667,
+  "<|26.06|>": 51668,
+  "<|26.08|>": 51669,
+  "<|26.10|>": 51670,
+  "<|26.12|>": 51671,
+  "<|26.14|>": 51672,
+  "<|26.16|>": 51673,
+  "<|26.18|>": 51674,
+  "<|26.20|>": 51675,
+  "<|26.22|>": 51676,
+  "<|26.24|>": 51677,
+  "<|26.26|>": 51678,
+  "<|26.28|>": 51679,
+  "<|26.30|>": 51680,
+  "<|26.32|>": 51681,
+  "<|26.34|>": 51682,
+  "<|26.36|>": 51683,
+  "<|26.38|>": 51684,
+  "<|26.40|>": 51685,
+  "<|26.42|>": 51686,
+  "<|26.44|>": 51687,
+  "<|26.46|>": 51688,
+  "<|26.48|>": 51689,
+  "<|26.50|>": 51690,
+  "<|26.52|>": 51691,
+  "<|26.54|>": 51692,
+  "<|26.56|>": 51693,
+  "<|26.58|>": 51694,
+  "<|26.60|>": 51695,
+  "<|26.62|>": 51696,
+  "<|26.64|>": 51697,
+  "<|26.66|>": 51698,
+  "<|26.68|>": 51699,
+  "<|26.70|>": 51700,
+  "<|26.72|>": 51701,
+  "<|26.74|>": 51702,
+  "<|26.76|>": 51703,
+  "<|26.78|>": 51704,
+  "<|26.80|>": 51705,
+  "<|26.82|>": 51706,
+  "<|26.84|>": 51707,
+  "<|26.86|>": 51708,
+  "<|26.88|>": 51709,
+  "<|26.90|>": 51710,
+  "<|26.92|>": 51711,
+  "<|26.94|>": 51712,
+  "<|26.96|>": 51713,
+  "<|26.98|>": 51714,
+  "<|27.00|>": 51715,
+  "<|27.02|>": 51716,
+  "<|27.04|>": 51717,
+  "<|27.06|>": 51718,
+  "<|27.08|>": 51719,
+  "<|27.10|>": 51720,
+  "<|27.12|>": 51721,
+  "<|27.14|>": 51722,
+  "<|27.16|>": 51723,
+  "<|27.18|>": 51724,
+  "<|27.20|>": 51725,
+  "<|27.22|>": 51726,
+  "<|27.24|>": 51727,
+  "<|27.26|>": 51728,
+  "<|27.28|>": 51729,
+  "<|27.30|>": 51730,
+  "<|27.32|>": 51731,
+  "<|27.34|>": 51732,
+  "<|27.36|>": 51733,
+  "<|27.38|>": 51734,
+  "<|27.40|>": 51735,
+  "<|27.42|>": 51736,
+  "<|27.44|>": 51737,
+  "<|27.46|>": 51738,
+  "<|27.48|>": 51739,
+  "<|27.50|>": 51740,
+  "<|27.52|>": 51741,
+  "<|27.54|>": 51742,
+  "<|27.56|>": 51743,
+  "<|27.58|>": 51744,
+  "<|27.60|>": 51745,
+  "<|27.62|>": 51746,
+  "<|27.64|>": 51747,
+  "<|27.66|>": 51748,
+  "<|27.68|>": 51749,
+  "<|27.70|>": 51750,
+  "<|27.72|>": 51751,
+  "<|27.74|>": 51752,
+  "<|27.76|>": 51753,
+  "<|27.78|>": 51754,
+  "<|27.80|>": 51755,
+  "<|27.82|>": 51756,
+  "<|27.84|>": 51757,
+  "<|27.86|>": 51758,
+  "<|27.88|>": 51759,
+  "<|27.90|>": 51760,
+  "<|27.92|>": 51761,
+  "<|27.94|>": 51762,
+  "<|27.96|>": 51763,
+  "<|27.98|>": 51764,
+  "<|28.00|>": 51765,
+  "<|28.02|>": 51766,
+  "<|28.04|>": 51767,
+  "<|28.06|>": 51768,
+  "<|28.08|>": 51769,
+  "<|28.10|>": 51770,
+  "<|28.12|>": 51771,
+  "<|28.14|>": 51772,
+  "<|28.16|>": 51773,
+  "<|28.18|>": 51774,
+  "<|28.20|>": 51775,
+  "<|28.22|>": 51776,
+  "<|28.24|>": 51777,
+  "<|28.26|>": 51778,
+  "<|28.28|>": 51779,
+  "<|28.30|>": 51780,
+  "<|28.32|>": 51781,
+  "<|28.34|>": 51782,
+  "<|28.36|>": 51783,
+  "<|28.38|>": 51784,
+  "<|28.40|>": 51785,
+  "<|28.42|>": 51786,
+  "<|28.44|>": 51787,
+  "<|28.46|>": 51788,
+  "<|28.48|>": 51789,
+  "<|28.50|>": 51790,
+  "<|28.52|>": 51791,
+  "<|28.54|>": 51792,
+  "<|28.56|>": 51793,
+  "<|28.58|>": 51794,
+  "<|28.60|>": 51795,
+  "<|28.62|>": 51796,
+  "<|28.64|>": 51797,
+  "<|28.66|>": 51798,
+  "<|28.68|>": 51799,
+  "<|28.70|>": 51800,
+  "<|28.72|>": 51801,
+  "<|28.74|>": 51802,
+  "<|28.76|>": 51803,
+  "<|28.78|>": 51804,
+  "<|28.80|>": 51805,
+  "<|28.82|>": 51806,
+  "<|28.84|>": 51807,
+  "<|28.86|>": 51808,
+  "<|28.88|>": 51809,
+  "<|28.90|>": 51810,
+  "<|28.92|>": 51811,
+  "<|28.94|>": 51812,
+  "<|28.96|>": 51813,
+  "<|28.98|>": 51814,
+  "<|29.00|>": 51815,
+  "<|29.02|>": 51816,
+  "<|29.04|>": 51817,
+  "<|29.06|>": 51818,
+  "<|29.08|>": 51819,
+  "<|29.10|>": 51820,
+  "<|29.12|>": 51821,
+  "<|29.14|>": 51822,
+  "<|29.16|>": 51823,
+  "<|29.18|>": 51824,
+  "<|29.20|>": 51825,
+  "<|29.22|>": 51826,
+  "<|29.24|>": 51827,
+  "<|29.26|>": 51828,
+  "<|29.28|>": 51829,
+  "<|29.30|>": 51830,
+  "<|29.32|>": 51831,
+  "<|29.34|>": 51832,
+  "<|29.36|>": 51833,
+  "<|29.38|>": 51834,
+  "<|29.40|>": 51835,
+  "<|29.42|>": 51836,
+  "<|29.44|>": 51837,
+  "<|29.46|>": 51838,
+  "<|29.48|>": 51839,
+  "<|29.50|>": 51840,
+  "<|29.52|>": 51841,
+  "<|29.54|>": 51842,
+  "<|29.56|>": 51843,
+  "<|29.58|>": 51844,
+  "<|29.60|>": 51845,
+  "<|29.62|>": 51846,
+  "<|29.64|>": 51847,
+  "<|29.66|>": 51848,
+  "<|29.68|>": 51849,
+  "<|29.70|>": 51850,
+  "<|29.72|>": 51851,
+  "<|29.74|>": 51852,
+  "<|29.76|>": 51853,
+  "<|29.78|>": 51854,
+  "<|29.80|>": 51855,
+  "<|29.82|>": 51856,
+  "<|29.84|>": 51857,
+  "<|29.86|>": 51858,
+  "<|29.88|>": 51859,
+  "<|29.90|>": 51860,
+  "<|29.92|>": 51861,
+  "<|29.94|>": 51862,
+  "<|29.96|>": 51863,
+  "<|29.98|>": 51864,
+  "<|3.00|>": 50515,
+  "<|3.02|>": 50516,
+  "<|3.04|>": 50517,
+  "<|3.06|>": 50518,
+  "<|3.08|>": 50519,
+  "<|3.10|>": 50520,
+  "<|3.12|>": 50521,
+  "<|3.14|>": 50522,
+  "<|3.16|>": 50523,
+  "<|3.18|>": 50524,
+  "<|3.20|>": 50525,
+  "<|3.22|>": 50526,
+  "<|3.24|>": 50527,
+  "<|3.26|>": 50528,
+  "<|3.28|>": 50529,
+  "<|3.30|>": 50530,
+  "<|3.32|>": 50531,
+  "<|3.34|>": 50532,
+  "<|3.36|>": 50533,
+  "<|3.38|>": 50534,
+  "<|3.40|>": 50535,
+  "<|3.42|>": 50536,
+  "<|3.44|>": 50537,
+  "<|3.46|>": 50538,
+  "<|3.48|>": 50539,
+  "<|3.50|>": 50540,
+  "<|3.52|>": 50541,
+  "<|3.54|>": 50542,
+  "<|3.56|>": 50543,
+  "<|3.58|>": 50544,
+  "<|3.60|>": 50545,
+  "<|3.62|>": 50546,
+  "<|3.64|>": 50547,
+  "<|3.66|>": 50548,
+  "<|3.68|>": 50549,
+  "<|3.70|>": 50550,
+  "<|3.72|>": 50551,
+  "<|3.74|>": 50552,
+  "<|3.76|>": 50553,
+  "<|3.78|>": 50554,
+  "<|3.80|>": 50555,
+  "<|3.82|>": 50556,
+  "<|3.84|>": 50557,
+  "<|3.86|>": 50558,
+  "<|3.88|>": 50559,
+  "<|3.90|>": 50560,
+  "<|3.92|>": 50561,
+  "<|3.94|>": 50562,
+  "<|3.96|>": 50563,
+  "<|3.98|>": 50564,
+  "<|30.00|>": 51865,
+  "<|4.00|>": 50565,
+  "<|4.02|>": 50566,
+  "<|4.04|>": 50567,
+  "<|4.06|>": 50568,
+  "<|4.08|>": 50569,
+  "<|4.10|>": 50570,
+  "<|4.12|>": 50571,
+  "<|4.14|>": 50572,
+  "<|4.16|>": 50573,
+  "<|4.18|>": 50574,
+  "<|4.20|>": 50575,
+  "<|4.22|>": 50576,
+  "<|4.24|>": 50577,
+  "<|4.26|>": 50578,
+  "<|4.28|>": 50579,
+  "<|4.30|>": 50580,
+  "<|4.32|>": 50581,
+  "<|4.34|>": 50582,
+  "<|4.36|>": 50583,
+  "<|4.38|>": 50584,
+  "<|4.40|>": 50585,
+  "<|4.42|>": 50586,
+  "<|4.44|>": 50587,
+  "<|4.46|>": 50588,
+  "<|4.48|>": 50589,
+  "<|4.50|>": 50590,
+  "<|4.52|>": 50591,
+  "<|4.54|>": 50592,
+  "<|4.56|>": 50593,
+  "<|4.58|>": 50594,
+  "<|4.60|>": 50595,
+  "<|4.62|>": 50596,
+  "<|4.64|>": 50597,
+  "<|4.66|>": 50598,
+  "<|4.68|>": 50599,
+  "<|4.70|>": 50600,
+  "<|4.72|>": 50601,
+  "<|4.74|>": 50602,
+  "<|4.76|>": 50603,
+  "<|4.78|>": 50604,
+  "<|4.80|>": 50605,
+  "<|4.82|>": 50606,
+  "<|4.84|>": 50607,
+  "<|4.86|>": 50608,
+  "<|4.88|>": 50609,
+  "<|4.90|>": 50610,
+  "<|4.92|>": 50611,
+  "<|4.94|>": 50612,
+  "<|4.96|>": 50613,
+  "<|4.98|>": 50614,
+  "<|5.00|>": 50615,
+  "<|5.02|>": 50616,
+  "<|5.04|>": 50617,
+  "<|5.06|>": 50618,
+  "<|5.08|>": 50619,
+  "<|5.10|>": 50620,
+  "<|5.12|>": 50621,
+  "<|5.14|>": 50622,
+  "<|5.16|>": 50623,
+  "<|5.18|>": 50624,
+  "<|5.20|>": 50625,
+  "<|5.22|>": 50626,
+  "<|5.24|>": 50627,
+  "<|5.26|>": 50628,
+  "<|5.28|>": 50629,
+  "<|5.30|>": 50630,
+  "<|5.32|>": 50631,
+  "<|5.34|>": 50632,
+  "<|5.36|>": 50633,
+  "<|5.38|>": 50634,
+  "<|5.40|>": 50635,
+  "<|5.42|>": 50636,
+  "<|5.44|>": 50637,
+  "<|5.46|>": 50638,
+  "<|5.48|>": 50639,
+  "<|5.50|>": 50640,
+  "<|5.52|>": 50641,
+  "<|5.54|>": 50642,
+  "<|5.56|>": 50643,
+  "<|5.58|>": 50644,
+  "<|5.60|>": 50645,
+  "<|5.62|>": 50646,
+  "<|5.64|>": 50647,
+  "<|5.66|>": 50648,
+  "<|5.68|>": 50649,
+  "<|5.70|>": 50650,
+  "<|5.72|>": 50651,
+  "<|5.74|>": 50652,
+  "<|5.76|>": 50653,
+  "<|5.78|>": 50654,
+  "<|5.80|>": 50655,
+  "<|5.82|>": 50656,
+  "<|5.84|>": 50657,
+  "<|5.86|>": 50658,
+  "<|5.88|>": 50659,
+  "<|5.90|>": 50660,
+  "<|5.92|>": 50661,
+  "<|5.94|>": 50662,
+  "<|5.96|>": 50663,
+  "<|5.98|>": 50664,
+  "<|6.00|>": 50665,
+  "<|6.02|>": 50666,
+  "<|6.04|>": 50667,
+  "<|6.06|>": 50668,
+  "<|6.08|>": 50669,
+  "<|6.10|>": 50670,
+  "<|6.12|>": 50671,
+  "<|6.14|>": 50672,
+  "<|6.16|>": 50673,
+  "<|6.18|>": 50674,
+  "<|6.20|>": 50675,
+  "<|6.22|>": 50676,
+  "<|6.24|>": 50677,
+  "<|6.26|>": 50678,
+  "<|6.28|>": 50679,
+  "<|6.30|>": 50680,
+  "<|6.32|>": 50681,
+  "<|6.34|>": 50682,
+  "<|6.36|>": 50683,
+  "<|6.38|>": 50684,
+  "<|6.40|>": 50685,
+  "<|6.42|>": 50686,
+  "<|6.44|>": 50687,
+  "<|6.46|>": 50688,
+  "<|6.48|>": 50689,
+  "<|6.50|>": 50690,
+  "<|6.52|>": 50691,
+  "<|6.54|>": 50692,
+  "<|6.56|>": 50693,
+  "<|6.58|>": 50694,
+  "<|6.60|>": 50695,
+  "<|6.62|>": 50696,
+  "<|6.64|>": 50697,
+  "<|6.66|>": 50698,
+  "<|6.68|>": 50699,
+  "<|6.70|>": 50700,
+  "<|6.72|>": 50701,
+  "<|6.74|>": 50702,
+  "<|6.76|>": 50703,
+  "<|6.78|>": 50704,
+  "<|6.80|>": 50705,
+  "<|6.82|>": 50706,
+  "<|6.84|>": 50707,
+  "<|6.86|>": 50708,
+  "<|6.88|>": 50709,
+  "<|6.90|>": 50710,
+  "<|6.92|>": 50711,
+  "<|6.94|>": 50712,
+  "<|6.96|>": 50713,
+  "<|6.98|>": 50714,
+  "<|7.00|>": 50715,
+  "<|7.02|>": 50716,
+  "<|7.04|>": 50717,
+  "<|7.06|>": 50718,
+  "<|7.08|>": 50719,
+  "<|7.10|>": 50720,
+  "<|7.12|>": 50721,
+  "<|7.14|>": 50722,
+  "<|7.16|>": 50723,
+  "<|7.18|>": 50724,
+  "<|7.20|>": 50725,
+  "<|7.22|>": 50726,
+  "<|7.24|>": 50727,
+  "<|7.26|>": 50728,
+  "<|7.28|>": 50729,
+  "<|7.30|>": 50730,
+  "<|7.32|>": 50731,
+  "<|7.34|>": 50732,
+  "<|7.36|>": 50733,
+  "<|7.38|>": 50734,
+  "<|7.40|>": 50735,
+  "<|7.42|>": 50736,
+  "<|7.44|>": 50737,
+  "<|7.46|>": 50738,
+  "<|7.48|>": 50739,
+  "<|7.50|>": 50740,
+  "<|7.52|>": 50741,
+  "<|7.54|>": 50742,
+  "<|7.56|>": 50743,
+  "<|7.58|>": 50744,
+  "<|7.60|>": 50745,
+  "<|7.62|>": 50746,
+  "<|7.64|>": 50747,
+  "<|7.66|>": 50748,
+  "<|7.68|>": 50749,
+  "<|7.70|>": 50750,
+  "<|7.72|>": 50751,
+  "<|7.74|>": 50752,
+  "<|7.76|>": 50753,
+  "<|7.78|>": 50754,
+  "<|7.80|>": 50755,
+  "<|7.82|>": 50756,
+  "<|7.84|>": 50757,
+  "<|7.86|>": 50758,
+  "<|7.88|>": 50759,
+  "<|7.90|>": 50760,
+  "<|7.92|>": 50761,
+  "<|7.94|>": 50762,
+  "<|7.96|>": 50763,
+  "<|7.98|>": 50764,
+  "<|8.00|>": 50765,
+  "<|8.02|>": 50766,
+  "<|8.04|>": 50767,
+  "<|8.06|>": 50768,
+  "<|8.08|>": 50769,
+  "<|8.10|>": 50770,
+  "<|8.12|>": 50771,
+  "<|8.14|>": 50772,
+  "<|8.16|>": 50773,
+  "<|8.18|>": 50774,
+  "<|8.20|>": 50775,
+  "<|8.22|>": 50776,
+  "<|8.24|>": 50777,
+  "<|8.26|>": 50778,
+  "<|8.28|>": 50779,
+  "<|8.30|>": 50780,
+  "<|8.32|>": 50781,
+  "<|8.34|>": 50782,
+  "<|8.36|>": 50783,
+  "<|8.38|>": 50784,
+  "<|8.40|>": 50785,
+  "<|8.42|>": 50786,
+  "<|8.44|>": 50787,
+  "<|8.46|>": 50788,
+  "<|8.48|>": 50789,
+  "<|8.50|>": 50790,
+  "<|8.52|>": 50791,
+  "<|8.54|>": 50792,
+  "<|8.56|>": 50793,
+  "<|8.58|>": 50794,
+  "<|8.60|>": 50795,
+  "<|8.62|>": 50796,
+  "<|8.64|>": 50797,
+  "<|8.66|>": 50798,
+  "<|8.68|>": 50799,
+  "<|8.70|>": 50800,
+  "<|8.72|>": 50801,
+  "<|8.74|>": 50802,
+  "<|8.76|>": 50803,
+  "<|8.78|>": 50804,
+  "<|8.80|>": 50805,
+  "<|8.82|>": 50806,
+  "<|8.84|>": 50807,
+  "<|8.86|>": 50808,
+  "<|8.88|>": 50809,
+  "<|8.90|>": 50810,
+  "<|8.92|>": 50811,
+  "<|8.94|>": 50812,
+  "<|8.96|>": 50813,
+  "<|8.98|>": 50814,
+  "<|9.00|>": 50815,
+  "<|9.02|>": 50816,
+  "<|9.04|>": 50817,
+  "<|9.06|>": 50818,
+  "<|9.08|>": 50819,
+  "<|9.10|>": 50820,
+  "<|9.12|>": 50821,
+  "<|9.14|>": 50822,
+  "<|9.16|>": 50823,
+  "<|9.18|>": 50824,
+  "<|9.20|>": 50825,
+  "<|9.22|>": 50826,
+  "<|9.24|>": 50827,
+  "<|9.26|>": 50828,
+  "<|9.28|>": 50829,
+  "<|9.30|>": 50830,
+  "<|9.32|>": 50831,
+  "<|9.34|>": 50832,
+  "<|9.36|>": 50833,
+  "<|9.38|>": 50834,
+  "<|9.40|>": 50835,
+  "<|9.42|>": 50836,
+  "<|9.44|>": 50837,
+  "<|9.46|>": 50838,
+  "<|9.48|>": 50839,
+  "<|9.50|>": 50840,
+  "<|9.52|>": 50841,
+  "<|9.54|>": 50842,
+  "<|9.56|>": 50843,
+  "<|9.58|>": 50844,
+  "<|9.60|>": 50845,
+  "<|9.62|>": 50846,
+  "<|9.64|>": 50847,
+  "<|9.66|>": 50848,
+  "<|9.68|>": 50849,
+  "<|9.70|>": 50850,
+  "<|9.72|>": 50851,
+  "<|9.74|>": 50852,
+  "<|9.76|>": 50853,
+  "<|9.78|>": 50854,
+  "<|9.80|>": 50855,
+  "<|9.82|>": 50856,
+  "<|9.84|>": 50857,
+  "<|9.86|>": 50858,
+  "<|9.88|>": 50859,
+  "<|9.90|>": 50860,
+  "<|9.92|>": 50861,
+  "<|9.94|>": 50862,
+  "<|9.96|>": 50863,
+  "<|9.98|>": 50864,
+  "<|af|>": 50327,
+  "<|am|>": 50334,
+  "<|ar|>": 50272,
+  "<|as|>": 50350,
+  "<|az|>": 50304,
+  "<|ba|>": 50355,
+  "<|be|>": 50330,
+  "<|bg|>": 50292,
+  "<|bn|>": 50302,
+  "<|bo|>": 50347,
+  "<|br|>": 50309,
+  "<|bs|>": 50315,
+  "<|ca|>": 50270,
+  "<|cs|>": 50283,
+  "<|cy|>": 50297,
+  "<|da|>": 50285,
+  "<|de|>": 50261,
+  "<|el|>": 50281,
+  "<|endoftext|>": 50257,
+  "<|en|>": 50259,
+  "<|es|>": 50262,
+  "<|et|>": 50307,
+  "<|eu|>": 50310,
+  "<|fa|>": 50300,
+  "<|fi|>": 50277,
+  "<|fo|>": 50338,
+  "<|fr|>": 50265,
+  "<|gl|>": 50319,
+  "<|gu|>": 50333,
+  "<|haw|>": 50352,
+  "<|ha|>": 50354,
+  "<|he|>": 50279,
+  "<|hi|>": 50276,
+  "<|hr|>": 50291,
+  "<|ht|>": 50339,
+  "<|hu|>": 50286,
+  "<|hy|>": 50312,
+  "<|id|>": 50275,
+  "<|is|>": 50311,
+  "<|it|>": 50274,
+  "<|ja|>": 50266,
+  "<|jw|>": 50356,
+  "<|ka|>": 50329,
+  "<|kk|>": 50316,
+  "<|km|>": 50323,
+  "<|kn|>": 50306,
+  "<|ko|>": 50264,
+  "<|la|>": 50294,
+  "<|lb|>": 50345,
+  "<|ln|>": 50353,
+  "<|lo|>": 50336,
+  "<|lt|>": 50293,
+  "<|lv|>": 50301,
+  "<|mg|>": 50349,
+  "<|mi|>": 50295,
+  "<|mk|>": 50308,
+  "<|ml|>": 50296,
+  "<|mn|>": 50314,
+  "<|mr|>": 50320,
+  "<|ms|>": 50282,
+  "<|mt|>": 50343,
+  "<|my|>": 50346,
+  "<|ne|>": 50313,
+  "<|nl|>": 50271,
+  "<|nn|>": 50342,
+  "<|nospeech|>": 50363,
+  "<|notimestamps|>": 50364,
+  "<|no|>": 50288,
+  "<|oc|>": 50328,
+  "<|pa|>": 50321,
+  "<|pl|>": 50269,
+  "<|ps|>": 50340,
+  "<|pt|>": 50267,
+  "<|ro|>": 50284,
+  "<|ru|>": 50263,
+  "<|sa|>": 50344,
+  "<|sd|>": 50332,
+  "<|si|>": 50322,
+  "<|sk|>": 50298,
+  "<|sl|>": 50305,
+  "<|sn|>": 50324,
+  "<|so|>": 50326,
+  "<|sq|>": 50317,
+  "<|sr|>": 50303,
+  "<|startoflm|>": 50361,
+  "<|startofprev|>": 50362,
+  "<|startoftranscript|>": 50258,
+  "<|su|>": 50357,
+  "<|sv|>": 50273,
+  "<|sw|>": 50318,
+  "<|ta|>": 50287,
+  "<|te|>": 50299,
+  "<|tg|>": 50331,
+  "<|th|>": 50289,
+  "<|tk|>": 50341,
+  "<|tl|>": 50348,
+  "<|transcribe|>": 50360,
+  "<|translate|>": 50359,
+  "<|tr|>": 50268,
+  "<|tt|>": 50351,
+  "<|uk|>": 50280,
+  "<|ur|>": 50290,
+  "<|uz|>": 50337,
+  "<|vi|>": 50278,
+  "<|yi|>": 50335,
+  "<|yo|>": 50325,
+  "<|yue|>": 50358,
+  "<|zh|>": 50260
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.006861437764047724,
+    "train_runtime": 11834.061,
+    "train_samples": 4118364,
+    "train_samples_per_second": 348.009,
+    "train_steps_per_second": 0.272
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "/home/azureuser/data2/models/crisper_whisper_verbatim_finetuned_de_en_swiss",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

generation_config.json

@@ -0,0 +1,745 @@
+{
+  "alignment_heads": [
+    [7, 0],
+    [10, 17],
+    [12, 18],
+    [13, 12],
+    [16, 1],
+    [17, 14],
+    [19, 11],
+    [21, 4],
+    [24, 1],
+    [25, 6]
+  ],
+  "begin_suppress_tokens": [],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [1, null],
+    [2, 50360]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "legacy": false,
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "median_filter_width": 3,
+  "no_timestamps_token_id": 50364,
+  "num_beams": 5,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50362,
+  "return_timestamps": true,
+  "suppress_tokens": [
+    1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90,
+    91, 92, 93, 256, 257, 261, 262, 269, 272, 274, 275, 276, 277, 280, 283, 286,
+    287, 288, 290, 294, 297, 307, 308, 309, 314, 316, 318, 319, 322, 333, 343,
+    344, 350, 359, 361, 363, 364, 367, 371, 372, 376, 382, 383, 389, 392, 398,
+    405, 412, 413, 417, 419, 420, 421, 422, 426, 430, 439, 441, 451, 455, 460,
+    462, 465, 474, 476, 479, 484, 497, 498, 502, 503, 505, 508, 517, 520, 522,
+    527, 531, 539, 542, 543, 546, 564, 566, 568, 588, 591, 594, 605, 614, 623,
+    624, 650, 669, 672, 675, 676, 680, 686, 690, 691, 696, 710, 711, 716, 720,
+    725, 741, 744, 752, 757, 764, 776, 785, 802, 803, 805, 806, 810, 825, 826,
+    846, 847, 859, 861, 871, 873, 875, 877, 893, 902, 917, 918, 922, 931, 948,
+    950, 975, 981, 997, 999, 1000, 1006, 1010, 1015, 1016, 1017, 1025, 1030,
+    1059, 1065, 1069, 1070, 1075, 1077, 1084, 1097, 1102, 1104, 1105, 1111,
+    1112, 1136, 1153, 1158, 1163, 1175, 1176, 1189, 1191, 1200, 1208, 1241,
+    1249, 1254, 1256, 1257, 1289, 1291, 1292, 1305, 1306, 1325, 1335, 1350,
+    1353, 1354, 1357, 1358, 1362, 1363, 1386, 1398, 1418, 1424, 1443, 1447,
+    1457, 1463, 1475, 1476, 1479, 1512, 1519, 1523, 1531, 1533, 1544, 1552,
+    1556, 1562, 1567, 1571, 1574, 1581, 1591, 1595, 1601, 1609, 1614, 1620,
+    1641, 1649, 1667, 1671, 1696, 1714, 1722, 1741, 1746, 1761, 1763, 1766,
+    1769, 1771, 1772, 1774, 1777, 1783, 1796, 1812, 1815, 1832, 1844, 1846,
+    1848, 1853, 1876, 1882, 1889, 1893, 1902, 1910, 1912, 1919, 1930, 1931,
+    1934, 1938, 1954, 1958, 1975, 1982, 1988, 1992, 1997, 2009, 2031, 2064,
+    2081, 2087, 2091, 2097, 2098, 2106, 2117, 2127, 2160, 2179, 2181, 2182,
+    2200, 2207, 2226, 2230, 2247, 2259, 2278, 2298, 2306, 2322, 2324, 2334,
+    2342, 2344, 2346, 2367, 2388, 2411, 2417, 2434, 2460, 2467, 2471, 2473,
+    2506, 2511, 2515, 2518, 2525, 2538, 2545, 2548, 2552, 2558, 2559, 2562,
+    2569, 2579, 2582, 2595, 2605, 2612, 2613, 2620, 2627, 2631, 2641, 2670,
+    2672, 2675, 2698, 2707, 2716, 2760, 2764, 2773, 2794, 2800, 2803, 2811,
+    2816, 2820, 2838, 2839, 2858, 2861, 2868, 2884, 2901, 2921, 2922, 2938,
+    2939, 2941, 2943, 2952, 2989, 2994, 3003, 3005, 3015, 3016, 3057, 3069,
+    3074, 3078, 3080, 3082, 3119, 3121, 3129, 3133, 3138, 3171, 3182, 3185,
+    3187, 3205, 3207, 3222, 3223, 3232, 3238, 3246, 3253, 3266, 3268, 3271,
+    3276, 3279, 3280, 3304, 3317, 3322, 3337, 3342, 3348, 3352, 3362, 3369,
+    3375, 3382, 3405, 3406, 3418, 3423, 3424, 3446, 3447, 3453, 3466, 3468,
+    3472, 3474, 3485, 3489, 3490, 3495, 3508, 3522, 3536, 3551, 3561, 3570,
+    3596, 3599, 3611, 3677, 3691, 3693, 3712, 3714, 3716, 3725, 3748, 3751,
+    3756, 3766, 3775, 3785, 3787, 3799, 3828, 3846, 3853, 3854, 3863, 3867,
+    3883, 3898, 3907, 3912, 3913, 3952, 3957, 3961, 3970, 3972, 4032, 4038,
+    4044, 4092, 4102, 4104, 4119, 4121, 4141, 4147, 4149, 4164, 4183, 4193,
+    4197, 4214, 4224, 4235, 4249, 4250, 4279, 4285, 4286, 4291, 4306, 4318,
+    4320, 4329, 4337, 4360, 4376, 4386, 4394, 4404, 4417, 4419, 4423, 4428,
+    4435, 4452, 4484, 4496, 4498, 4504, 4506, 4520, 4540, 4550, 4572, 4575,
+    4590, 4647, 4654, 4667, 4677, 4684, 4687, 4702, 4704, 4709, 4717, 4724,
+    4762, 4773, 4792, 4815, 4823, 4834, 4849, 4873, 4875, 4915, 4916, 4917,
+    4925, 4938, 4946, 4952, 4954, 4955, 4977, 4987, 4995, 5009, 5019, 5051,
+    5059, 5080, 5092, 5093, 5096, 5099, 5106, 5134, 5148, 5156, 5161, 5188,
+    5194, 5199, 5200, 5205, 5211, 5225, 5239, 5252, 5254, 5260, 5277, 5289,
+    5294, 5296, 5297, 5314, 5335, 5337, 5345, 5348, 5356, 5357, 5360, 5365,
+    5372, 5374, 5386, 5390, 5406, 5408, 5420, 5431, 5442, 5449, 5453, 5457,
+    5478, 5479, 5485, 5500, 5532, 5537, 5539, 5540, 5542, 5543, 5544, 5572,
+    5579, 5594, 5614, 5616, 5638, 5643, 5650, 5667, 5670, 5685, 5691, 5693,
+    5706, 5710, 5713, 5714, 5721, 5723, 5727, 5738, 5747, 5750, 5779, 5786,
+    5790, 5792, 5799, 5814, 5815, 5842, 5851, 5854, 5867, 5872, 5875, 5899,
+    5901, 5937, 5941, 5948, 5955, 5958, 5959, 5960, 5973, 5976, 5995, 6021,
+    6027, 6032, 6035, 6037, 6040, 6048, 6053, 6054, 6055, 6074, 6092, 6106,
+    6107, 6113, 6120, 6125, 6138, 6145, 6151, 6156, 6160, 6166, 6169, 6170,
+    6196, 6197, 6198, 6203, 6205, 6206, 6209, 6214, 6225, 6245, 6258, 6271,
+    6294, 6302, 6315, 6326, 6360, 6363, 6371, 6390, 6402, 6410, 6415, 6442,
+    6446, 6448, 6455, 6461, 6462, 6468, 6472, 6475, 6494, 6497, 6509, 6522,
+    6524, 6540, 6546, 6569, 6578, 6585, 6590, 6592, 6617, 6629, 6635, 6639,
+    6647, 6650, 6652, 6663, 6672, 6691, 6703, 6742, 6748, 6753, 6756, 6763,
+    6768, 6775, 6778, 6780, 6783, 6799, 6802, 6840, 6845, 6861, 6866, 6877,
+    6879, 6891, 6892, 6903, 6925, 6931, 6955, 6971, 6983, 6991, 7011, 7035,
+    7039, 7047, 7053, 7056, 7057, 7082, 7100, 7129, 7143, 7146, 7165, 7167,
+    7171, 7175, 7191, 7192, 7202, 7217, 7219, 7251, 7271, 7273, 7275, 7276,
+    7348, 7352, 7357, 7374, 7385, 7408, 7414, 7438, 7444, 7449, 7450, 7460,
+    7462, 7469, 7490, 7494, 7523, 7526, 7556, 7565, 7570, 7572, 7574, 7604,
+    7610, 7629, 7653, 7666, 7668, 7682, 7683, 7686, 7691, 7692, 7707, 7723,
+    7729, 7743, 7757, 7771, 7773, 7774, 7821, 7827, 7828, 7834, 7835, 7839,
+    7841, 7845, 7846, 7852, 7862, 7865, 7868, 7876, 7879, 7883, 7911, 7924,
+    7946, 7949, 7960, 7971, 7981, 7990, 7996, 8002, 8014, 8029, 8031, 8032,
+    8035, 8037, 8066, 8068, 8093, 8097, 8101, 8102, 8103, 8111, 8121, 8124,
+    8128, 8150, 8154, 8157, 8159, 8168, 8169, 8202, 8210, 8229, 8264, 8284,
+    8297, 8299, 8308, 8329, 8347, 8355, 8373, 8376, 8384, 8391, 8394, 8404,
+    8417, 8421, 8425, 8428, 8429, 8442, 8448, 8449, 8453, 8463, 8465, 8468,
+    8476, 8485, 8493, 8506, 8508, 8517, 8520, 8524, 8547, 8556, 8558, 8563,
+    8578, 8580, 8604, 8608, 8618, 8624, 8672, 8675, 8692, 8696, 8699, 8710,
+    8715, 8717, 8748, 8750, 8757, 8768, 8793, 8794, 8814, 8829, 8835, 8841,
+    8872, 8887, 8912, 8920, 8934, 8936, 8940, 8943, 8954, 8981, 8995, 8997,
+    9000, 9023, 9025, 9032, 9047, 9050, 9055, 9061, 9073, 9076, 9077, 9092,
+    9120, 9122, 9132, 9135, 9136, 9139, 9144, 9148, 9161, 9162, 9171, 9179,
+    9202, 9207, 9216, 9218, 9223, 9262, 9277, 9290, 9291, 9299, 9308, 9326,
+    9342, 9356, 9371, 9383, 9385, 9389, 9414, 9427, 9443, 9485, 9496, 9498,
+    9503, 9505, 9507, 9513, 9526, 9539, 9578, 9597, 9611, 9620, 9642, 9646,
+    9664, 9671, 9710, 9726, 9733, 9765, 9767, 9768, 9783, 9789, 9791, 9800,
+    9817, 9826, 9835, 9838, 9895, 9966, 9969, 10010, 10022, 10051, 10076, 10119,
+    10134, 10146, 10156, 10161, 10167, 10170, 10175, 10198, 10211, 10216, 10230,
+    10240, 10244, 10269, 10276, 10288, 10301, 10302, 10312, 10318, 10324, 10338,
+    10341, 10342, 10345, 10386, 10398, 10400, 10409, 10418, 10428, 10438, 10441,
+    10453, 10467, 10521, 10536, 10541, 10544, 10549, 10554, 10557, 10558, 10565,
+    10600, 10602, 10626, 10637, 10643, 10664, 10671, 10683, 10685, 10695, 10701,
+    10708, 10721, 10730, 10741, 10743, 10757, 10792, 10794, 10813, 10817, 10829,
+    10844, 10846, 10865, 10869, 10874, 10880, 10884, 10889, 10909, 10914, 10927,
+    10929, 10930, 10941, 10990, 11014, 11020, 11021, 11023, 11045, 11048, 11063,
+    11089, 11135, 11149, 11162, 11169, 11176, 11179, 11196, 11205, 11231, 11243,
+    11264, 11276, 11286, 11289, 11295, 11300, 11302, 11309, 11314, 11318, 11331,
+    11378, 11383, 11412, 11423, 11435, 11437, 11440, 11452, 11464, 11473, 11474,
+    11481, 11491, 11492, 11496, 11509, 11516, 11520, 11529, 11531, 11541, 11575,
+    11582, 11584, 11591, 11601, 11605, 11608, 11609, 11617, 11637, 11644, 11645,
+    11649, 11658, 11665, 11683, 11721, 11723, 11726, 11727, 11728, 11738, 11742,
+    11747, 11755, 11762, 11771, 11775, 11778, 11780, 11799, 11803, 11806, 11810,
+    11814, 11816, 11820, 11834, 11839, 11857, 11871, 11880, 11881, 11887, 11896,
+    11901, 11911, 11927, 11930, 11938, 11947, 11953, 11958, 11963, 11967, 11979,
+    11980, 11988, 11994, 12004, 12008, 12012, 12032, 12033, 12037, 12038, 12047,
+    12080, 12085, 12086, 12104, 12112, 12118, 12138, 12174, 12176, 12191, 12194,
+    12199, 12202, 12203, 12222, 12241, 12253, 12272, 12274, 12280, 12299, 12303,
+    12312, 12321, 12322, 12329, 12331, 12352, 12357, 12372, 12400, 12401, 12402,
+    12405, 12410, 12415, 12418, 12421, 12423, 12438, 12439, 12446, 12474, 12484,
+    12485, 12490, 12491, 12500, 12503, 12507, 12516, 12528, 12541, 12562, 12564,
+    12566, 12567, 12586, 12587, 12588, 12596, 12602, 12622, 12630, 12638, 12665,
+    12670, 12671, 12681, 12694, 12702, 12707, 12723, 12731, 12735, 12746, 12747,
+    12782, 12790, 12794, 12795, 12815, 12816, 12834, 12843, 12861, 12863, 12864,
+    12892, 12926, 12942, 12954, 12967, 12986, 12997, 13025, 13042, 13054, 13067,
+    13084, 13087, 13092, 13136, 13162, 13178, 13195, 13217, 13225, 13228, 13243,
+    13247, 13248, 13253, 13255, 13267, 13278, 13301, 13302, 13305, 13309, 13318,
+    13323, 13332, 13342, 13359, 13361, 13368, 13376, 13379, 13403, 13406, 13412,
+    13416, 13435, 13450, 13462, 13471, 13479, 13496, 13498, 13499, 13506, 13507,
+    13513, 13528, 13529, 13535, 13559, 13562, 13584, 13595, 13604, 13622, 13628,
+    13647, 13659, 13664, 13675, 13680, 13686, 13688, 13690, 13708, 13711, 13721,
+    13731, 13733, 13741, 13769, 13770, 13774, 13786, 13790, 13793, 13803, 13808,
+    13832, 13853, 13858, 13862, 13867, 13868, 13872, 13907, 13908, 13911, 13963,
+    13965, 13966, 13979, 13981, 13987, 13994, 14014, 14030, 14039, 14045, 14061,
+    14066, 14076, 14085, 14087, 14094, 14098, 14102, 14107, 14112, 14127, 14146,
+    14157, 14173, 14177, 14187, 14189, 14208, 14227, 14233, 14252, 14267, 14271,
+    14272, 14278, 14282, 14314, 14359, 14360, 14370, 14376, 14384, 14389, 14393,
+    14396, 14406, 14408, 14409, 14411, 14423, 14426, 14430, 14436, 14445, 14452,
+    14461, 14473, 14477, 14495, 14506, 14508, 14520, 14521, 14539, 14552, 14555,
+    14562, 14566, 14579, 14583, 14584, 14585, 14591, 14597, 14599, 14604, 14605,
+    14610, 14626, 14627, 14635, 14645, 14649, 14664, 14671, 14677, 14683, 14693,
+    14701, 14736, 14758, 14779, 14792, 14794, 14796, 14803, 14822, 14828, 14831,
+    14833, 14841, 14854, 14864, 14881, 14891, 14913, 14919, 14929, 14937, 14972,
+    14979, 14983, 14995, 15014, 15015, 15017, 15025, 15038, 15055, 15087, 15091,
+    15096, 15098, 15104, 15111, 15125, 15129, 15131, 15138, 15142, 15161, 15168,
+    15170, 15175, 15178, 15179, 15181, 15186, 15197, 15208, 15210, 15219, 15229,
+    15233, 15234, 15238, 15241, 15244, 15265, 15275, 15281, 15295, 15312, 15313,
+    15318, 15346, 15372, 15373, 15376, 15384, 15385, 15406, 15413, 15426, 15427,
+    15431, 15441, 15453, 15454, 15456, 15459, 15465, 15495, 15496, 15497, 15526,
+    15529, 15536, 15565, 15591, 15608, 15610, 15615, 15618, 15628, 15675, 15677,
+    15683, 15690, 15693, 15707, 15718, 15723, 15752, 15784, 15787, 15794, 15805,
+    15810, 15814, 15816, 15819, 15823, 15830, 15839, 15848, 15869, 15875, 15886,
+    15905, 15921, 15930, 15937, 15946, 15947, 15951, 15952, 15958, 15962, 15967,
+    15970, 15975, 15982, 15988, 16036, 16044, 16050, 16055, 16081, 16108, 16112,
+    16116, 16129, 16136, 16177, 16182, 16216, 16218, 16226, 16236, 16237, 16241,
+    16256, 16257, 16281, 16284, 16296, 16342, 16344, 16362, 16369, 16374, 16398,
+    16399, 16408, 16412, 16413, 16414, 16422, 16443, 16472, 16478, 16482, 16486,
+    16490, 16503, 16504, 16508, 16513, 16514, 16528, 16537, 16543, 16547, 16553,
+    16554, 16582, 16585, 16587, 16604, 16614, 16639, 16643, 16647, 16653, 16655,
+    16746, 16751, 16753, 16759, 16760, 16767, 16792, 16793, 16794, 16798, 16806,
+    16817, 16818, 16824, 16833, 16851, 16867, 16884, 16896, 16900, 16903, 16924,
+    16931, 16938, 16953, 16954, 16955, 16964, 17000, 17002, 17006, 17024, 17044,
+    17066, 17067, 17074, 17086, 17087, 17093, 17097, 17098, 17109, 17117, 17138,
+    17155, 17158, 17165, 17170, 17184, 17188, 17189, 17190, 17191, 17210, 17227,
+    17228, 17230, 17239, 17243, 17246, 17255, 17265, 17269, 17282, 17290, 17292,
+    17293, 17298, 17305, 17308, 17317, 17318, 17319, 17345, 17349, 17356, 17367,
+    17374, 17377, 17386, 17393, 17397, 17422, 17427, 17429, 17433, 17437, 17453,
+    17458, 17460, 17464, 17493, 17497, 17505, 17507, 17519, 17524, 17531, 17533,
+    17539, 17557, 17566, 17567, 17579, 17590, 17593, 17606, 17622, 17624, 17648,
+    17680, 17685, 17697, 17698, 17700, 17705, 17718, 17723, 17799, 17802, 17804,
+    17807, 17810, 17835, 17836, 17850, 17859, 17861, 17863, 17869, 17882, 17886,
+    17888, 17892, 17914, 17919, 17921, 17922, 17925, 17927, 17940, 17950, 17953,
+    17974, 17975, 18003, 18014, 18020, 18035, 18044, 18048, 18050, 18052, 18063,
+    18079, 18080, 18088, 18105, 18133, 18151, 18160, 18170, 18172, 18173, 18193,
+    18197, 18198, 18217, 18219, 18220, 18231, 18249, 18251, 18256, 18267, 18275,
+    18278, 18281, 18284, 18295, 18300, 18302, 18316, 18339, 18345, 18353, 18357,
+    18358, 18362, 18371, 18402, 18404, 18421, 18425, 18445, 18447, 18448, 18450,
+    18462, 18465, 18469, 18542, 18547, 18548, 18570, 18575, 18582, 18592, 18598,
+    18608, 18619, 18621, 18625, 18645, 18648, 18663, 18682, 18684, 18688, 18692,
+    18696, 18700, 18705, 18710, 18716, 18726, 18752, 18761, 18767, 18787, 18795,
+    18796, 18797, 18802, 18815, 18818, 18819, 18821, 18822, 18823, 18837, 18841,
+    18847, 18860, 18870, 18882, 18884, 18924, 18934, 18953, 18954, 18956, 18968,
+    18979, 18981, 18996, 19021, 19028, 19041, 19048, 19050, 19052, 19062, 19081,
+    19090, 19096, 19099, 19111, 19116, 19125, 19130, 19140, 19145, 19159, 19166,
+    19171, 19186, 19194, 19203, 19220, 19224, 19225, 19238, 19242, 19262, 19272,
+    19281, 19287, 19290, 19300, 19304, 19323, 19325, 19337, 19338, 19339, 19353,
+    19377, 19393, 19395, 19427, 19435, 19440, 19446, 19466, 19468, 19500, 19508,
+    19513, 19521, 19525, 19529, 19533, 19537, 19558, 19575, 19588, 19614, 19619,
+    19625, 19639, 19650, 19654, 19657, 19675, 19686, 19687, 19702, 19713, 19739,
+    19744, 19767, 19773, 19776, 19782, 19785, 19816, 19834, 19862, 19866, 19868,
+    19872, 19877, 19894, 19901, 19905, 19919, 19920, 19929, 19932, 19947, 19970,
+    19988, 19990, 20007, 20018, 20021, 20033, 20034, 20038, 20048, 20056, 20057,
+    20058, 20060, 20062, 20071, 20075, 20094, 20106, 20120, 20122, 20133, 20140,
+    20144, 20160, 20184, 20193, 20202, 20214, 20270, 20320, 20325, 20327, 20328,
+    20332, 20343, 20352, 20356, 20361, 20367, 20371, 20376, 20413, 20422, 20442,
+    20455, 20462, 20467, 20479, 20480, 20510, 20516, 20534, 20544, 20552, 20557,
+    20579, 20592, 20593, 20595, 20602, 20612, 20614, 20621, 20632, 20646, 20654,
+    20655, 20661, 20664, 20686, 20701, 20713, 20721, 20724, 20731, 20732, 20735,
+    20737, 20739, 20756, 20761, 20769, 20771, 20775, 20784, 20785, 20791, 20793,
+    20804, 20827, 20835, 20836, 20839, 20846, 20865, 20876, 20883, 20892, 20901,
+    20914, 20940, 20941, 20943, 20955, 20966, 20979, 20981, 20990, 21018, 21021,
+    21036, 21040, 21048, 21050, 21061, 21070, 21074, 21093, 21123, 21125, 21126,
+    21141, 21150, 21151, 21163, 21168, 21171, 21172, 21173, 21190, 21196, 21199,
+    21204, 21210, 21211, 21213, 21225, 21248, 21271, 21272, 21288, 21299, 21306,
+    21316, 21322, 21325, 21326, 21330, 21353, 21361, 21376, 21393, 21423, 21427,
+    21441, 21442, 21454, 21461, 21463, 21484, 21491, 21520, 21541, 21553, 21561,
+    21568, 21570, 21591, 21593, 21600, 21601, 21614, 21624, 21640, 21642, 21657,
+    21664, 21675, 21723, 21736, 21753, 21760, 21763, 21771, 21777, 21786, 21787,
+    21790, 21819, 21822, 21825, 21831, 21845, 21848, 21851, 21860, 21869, 21874,
+    21879, 21887, 21904, 21923, 21924, 21929, 21955, 21959, 21970, 22008, 22018,
+    22026, 22038, 22050, 22069, 22088, 22103, 22104, 22105, 22114, 22116, 22136,
+    22164, 22170, 22174, 22178, 22199, 22211, 22226, 22233, 22249, 22253, 22256,
+    22259, 22274, 22282, 22285, 22296, 22326, 22332, 22337, 22345, 22355, 22357,
+    22366, 22392, 22396, 22403, 22414, 22423, 22431, 22450, 22458, 22464, 22473,
+    22475, 22493, 22513, 22514, 22516, 22520, 22530, 22531, 22547, 22552, 22554,
+    22559, 22575, 22598, 22610, 22626, 22628, 22630, 22638, 22660, 22672, 22681,
+    22692, 22723, 22726, 22746, 22757, 22766, 22773, 22776, 22779, 22784, 22785,
+    22786, 22789, 22791, 22806, 22809, 22817, 22826, 22830, 22835, 22839, 22841,
+    22845, 22852, 22859, 22864, 22882, 22892, 22896, 22917, 22922, 22941, 22949,
+    22955, 22980, 22993, 23018, 23019, 23023, 23032, 23040, 23045, 23056, 23062,
+    23065, 23093, 23095, 23097, 23103, 23113, 23130, 23156, 23157, 23159, 23174,
+    23183, 23185, 23188, 23189, 23212, 23218, 23227, 23232, 23251, 23252, 23271,
+    23277, 23298, 23301, 23324, 23332, 23355, 23356, 23378, 23397, 23399, 23401,
+    23409, 23411, 23429, 23442, 23459, 23466, 23480, 23483, 23490, 23501, 23504,
+    23517, 23524, 23534, 23538, 23564, 23566, 23567, 23568, 23571, 23572, 23576,
+    23589, 23593, 23594, 23609, 23620, 23624, 23662, 23678, 23681, 23685, 23695,
+    23698, 23706, 23717, 23727, 23728, 23733, 23744, 23745, 23748, 23754, 23761,
+    23762, 23779, 23788, 23805, 23811, 23822, 23828, 23850, 23851, 23879, 23883,
+    23896, 23914, 23919, 23932, 23943, 23967, 23969, 23971, 23977, 23981, 23985,
+    24000, 24011, 24036, 24040, 24052, 24072, 24107, 24119, 24124, 24154, 24162,
+    24223, 24226, 24258, 24262, 24263, 24267, 24268, 24284, 24288, 24301, 24333,
+    24346, 24364, 24382, 24393, 24394, 24407, 24419, 24425, 24431, 24437, 24450,
+    24452, 24457, 24466, 24471, 24504, 24513, 24540, 24570, 24587, 24599, 24624,
+    24633, 24637, 24640, 24641, 24659, 24665, 24673, 24688, 24689, 24697, 24761,
+    24789, 24803, 24806, 24824, 24841, 24848, 24852, 24870, 24872, 24873, 24879,
+    24882, 24888, 24895, 24899, 24902, 24906, 24907, 24915, 24938, 24961, 24981,
+    24985, 24997, 24999, 25016, 25022, 25023, 25026, 25030, 25041, 25052, 25064,
+    25072, 25073, 25090, 25095, 25111, 25112, 25117, 25134, 25141, 25152, 25181,
+    25192, 25202, 25210, 25220, 25222, 25223, 25224, 25228, 25241, 25249, 25253,
+    25259, 25260, 25261, 25267, 25279, 25286, 25291, 25295, 25299, 25311, 25324,
+    25330, 25331, 25336, 25340, 25348, 25361, 25376, 25387, 25394, 25402, 25407,
+    25412, 25416, 25420, 25423, 25424, 25429, 25439, 25442, 25448, 25451, 25456,
+    25461, 25477, 25478, 25488, 25502, 25505, 25519, 25546, 25548, 25554, 25573,
+    25581, 25592, 25594, 25597, 25600, 25609, 25614, 25619, 25627, 25643, 25659,
+    25680, 25685, 25690, 25709, 25713, 25714, 25715, 25716, 25719, 25743, 25744,
+    25762, 25769, 25777, 25782, 25788, 25793, 25809, 25810, 25830, 25850, 25858,
+    25859, 25867, 25869, 25884, 25888, 25891, 25892, 25900, 25901, 25931, 25936,
+    25954, 25959, 25962, 25965, 25966, 25970, 25975, 25989, 25992, 26015, 26022,
+    26029, 26031, 26040, 26050, 26061, 26063, 26072, 26078, 26080, 26082, 26130,
+    26141, 26142, 26151, 26158, 26161, 26163, 26188, 26189, 26219, 26235, 26236,
+    26260, 26283, 26288, 26307, 26308, 26322, 26326, 26332, 26355, 26367, 26375,
+    26386, 26393, 26413, 26421, 26430, 26434, 26435, 26459, 26465, 26498, 26530,
+    26532, 26536, 26541, 26560, 26577, 26578, 26579, 26585, 26616, 26624, 26634,
+    26647, 26649, 26660, 26683, 26684, 26685, 26687, 26693, 26700, 26709, 26713,
+    26722, 26727, 26732, 26738, 26765, 26767, 26769, 26790, 26795, 26799, 26809,
+    26815, 26822, 26825, 26830, 26859, 26861, 26864, 26869, 26882, 26896, 26915,
+    26923, 26926, 26930, 26932, 26936, 26939, 26953, 26969, 26974, 27005, 27010,
+    27021, 27037, 27057, 27061, 27084, 27102, 27123, 27133, 27160, 27166, 27168,
+    27170, 27178, 27184, 27195, 27253, 27265, 27268, 27276, 27289, 27298, 27309,
+    27321, 27338, 27343, 27358, 27362, 27375, 27378, 27399, 27409, 27414, 27454,
+    27461, 27476, 27547, 27553, 27565, 27580, 27583, 27597, 27604, 27612, 27616,
+    27619, 27630, 27644, 27647, 27657, 27675, 27676, 27680, 27685, 27686, 27689,
+    27690, 27692, 27705, 27707, 27718, 27727, 27728, 27730, 27735, 27750, 27763,
+    27770, 27777, 27779, 27786, 27810, 27818, 27842, 27850, 27855, 27857, 27900,
+    27902, 27917, 27921, 27930, 27934, 27949, 27984, 27990, 27994, 28005, 28012,
+    28019, 28031, 28037, 28042, 28045, 28049, 28052, 28063, 28082, 28109, 28110,
+    28126, 28135, 28155, 28168, 28186, 28197, 28206, 28211, 28215, 28225, 28227,
+    28251, 28255, 28263, 28266, 28274, 28277, 28279, 28280, 28285, 28308, 28316,
+    28321, 28340, 28349, 28353, 28378, 28379, 28386, 28404, 28408, 28409, 28411,
+    28433, 28451, 28459, 28484, 28499, 28501, 28512, 28516, 28561, 28589, 28608,
+    28615, 28644, 28654, 28669, 28674, 28678, 28697, 28705, 28720, 28722, 28740,
+    28743, 28773, 28774, 28808, 28814, 28819, 28820, 28829, 28830, 28838, 28846,
+    28850, 28851, 28857, 28858, 28862, 28864, 28865, 28871, 28876, 28888, 28890,
+    28909, 28910, 28915, 28919, 28930, 28947, 28952, 28966, 28985, 28987, 28991,
+    29006, 29018, 29020, 29027, 29033, 29038, 29042, 29081, 29083, 29113, 29114,
+    29130, 29141, 29151, 29153, 29155, 29159, 29165, 29175, 29176, 29178, 29211,
+    29215, 29217, 29221, 29232, 29251, 29258, 29273, 29274, 29282, 29292, 29302,
+    29307, 29331, 29341, 29346, 29355, 29356, 29367, 29386, 29396, 29403, 29421,
+    29427, 29431, 29437, 29438, 29443, 29462, 29464, 29481, 29488, 29491, 29511,
+    29521, 29530, 29543, 29545, 29578, 29581, 29589, 29612, 29644, 29646, 29647,
+    29660, 29677, 29678, 29681, 29684, 29696, 29697, 29702, 29725, 29727, 29745,
+    29748, 29752, 29761, 29773, 29777, 29778, 29779, 29797, 29802, 29814, 29821,
+    29850, 29853, 29858, 29860, 29861, 29872, 29874, 29886, 29888, 29898, 29909,
+    29910, 29913, 29928, 29936, 29958, 29984, 29988, 29994, 30010, 30014, 30027,
+    30031, 30056, 30065, 30069, 30075, 30081, 30086, 30092, 30094, 30131, 30152,
+    30155, 30171, 30181, 30184, 30189, 30196, 30203, 30241, 30275, 30277, 30283,
+    30290, 30323, 30338, 30342, 30366, 30372, 30401, 30402, 30414, 30417, 30418,
+    30427, 30455, 30463, 30474, 30476, 30480, 30484, 30505, 30516, 30519, 30526,
+    30534, 30537, 30555, 30560, 30574, 30596, 30600, 30602, 30604, 30605, 30612,
+    30620, 30624, 30663, 30668, 30673, 30680, 30682, 30693, 30695, 30696, 30704,
+    30711, 30722, 30724, 30743, 30754, 30757, 30767, 30774, 30778, 30787, 30794,
+    30825, 30849, 30863, 30886, 30890, 30907, 30908, 30917, 30926, 30937, 30939,
+    30942, 30953, 30971, 30974, 30977, 30989, 30999, 31002, 31004, 31016, 31030,
+    31035, 31051, 31064, 31065, 31072, 31076, 31079, 31099, 31121, 31128, 31131,
+    31135, 31138, 31155, 31170, 31179, 31181, 31184, 31186, 31187, 31202, 31208,
+    31233, 31239, 31253, 31254, 31278, 31279, 31287, 31293, 31305, 31321, 31332,
+    31335, 31363, 31376, 31378, 31455, 31461, 31462, 31471, 31473, 31482, 31488,
+    31495, 31496, 31498, 31500, 31526, 31537, 31546, 31560, 31577, 31590, 31618,
+    31624, 31630, 31636, 31637, 31638, 31645, 31650, 31651, 31655, 31673, 31681,
+    31684, 31701, 31714, 31725, 31733, 31736, 31751, 31765, 31778, 31790, 31798,
+    31835, 31842, 31849, 31852, 31854, 31855, 31859, 31862, 31863, 31877, 31879,
+    31883, 31890, 31900, 31913, 31916, 31936, 31964, 31983, 31990, 32008, 32023,
+    32038, 32041, 32047, 32052, 32068, 32084, 32098, 32104, 32106, 32111, 32117,
+    32145, 32147, 32164, 32167, 32172, 32188, 32226, 32239, 32255, 32257, 32263,
+    32266, 32277, 32278, 32293, 32297, 32298, 32302, 32314, 32315, 32329, 32346,
+    32348, 32373, 32387, 32388, 32393, 32409, 32412, 32413, 32415, 32416, 32468,
+    32470, 32480, 32481, 32498, 32500, 32505, 32546, 32547, 32576, 32578, 32582,
+    32599, 32604, 32606, 32609, 32610, 32620, 32628, 32648, 32656, 32685, 32700,
+    32709, 32724, 32725, 32726, 32743, 32767, 32771, 32779, 32787, 32790, 32792,
+    32803, 32818, 32825, 32831, 32848, 32855, 32875, 32876, 32889, 32892, 32902,
+    32914, 32922, 32925, 32926, 32937, 32942, 32944, 32946, 32948, 32960, 32977,
+    32987, 33019, 33042, 33058, 33079, 33093, 33114, 33115, 33128, 33136, 33179,
+    33180, 33181, 33195, 33200, 33206, 33210, 33214, 33229, 33236, 33243, 33244,
+    33248, 33263, 33274, 33292, 33306, 33309, 33313, 33315, 33328, 33339, 33348,
+    33381, 33382, 33386, 33396, 33406, 33407, 33423, 33424, 33426, 33432, 33439,
+    33449, 33456, 33465, 33469, 33471, 33476, 33481, 33503, 33507, 33518, 33523,
+    33534, 33542, 33544, 33549, 33553, 33564, 33565, 33567, 33576, 33594, 33614,
+    33622, 33629, 33653, 33670, 33684, 33685, 33686, 33687, 33710, 33712, 33714,
+    33727, 33732, 33742, 33743, 33748, 33749, 33754, 33785, 33791, 33810, 33815,
+    33824, 33830, 33842, 33849, 33853, 33874, 33881, 33886, 33887, 33891, 33893,
+    33895, 33898, 33903, 33908, 33922, 33936, 33937, 33938, 33943, 33969, 33977,
+    33986, 33996, 34000, 34002, 34010, 34026, 34033, 34067, 34075, 34080, 34091,
+    34096, 34099, 34109, 34110, 34114, 34120, 34125, 34150, 34178, 34189, 34191,
+    34194, 34209, 34213, 34216, 34224, 34263, 34267, 34319, 34334, 34339, 34354,
+    34355, 34368, 34370, 34378, 34384, 34394, 34402, 34436, 34438, 34476, 34479,
+    34486, 34503, 34559, 34569, 34598, 34605, 34606, 34616, 34625, 34632, 34633,
+    34636, 34651, 34655, 34658, 34679, 34680, 34686, 34698, 34724, 34725, 34734,
+    34741, 34761, 34763, 34766, 34784, 34787, 34798, 34805, 34821, 34832, 34835,
+    34840, 34859, 34860, 34885, 34890, 34896, 34899, 34914, 34940, 34980, 34985,
+    34990, 34994, 35000, 35008, 35015, 35016, 35023, 35034, 35035, 35036, 35040,
+    35043, 35065, 35066, 35069, 35072, 35073, 35074, 35117, 35124, 35126, 35135,
+    35137, 35139, 35143, 35164, 35168, 35176, 35186, 35203, 35222, 35227, 35238,
+    35251, 35256, 35265, 35270, 35293, 35294, 35298, 35299, 35318, 35320, 35329,
+    35349, 35350, 35362, 35372, 35414, 35417, 35418, 35421, 35425, 35436, 35461,
+    35464, 35473, 35486, 35491, 35492, 35500, 35514, 35525, 35544, 35545, 35546,
+    35547, 35549, 35559, 35562, 35565, 35569, 35578, 35596, 35600, 35609, 35633,
+    35637, 35641, 35650, 35656, 35666, 35676, 35692, 35717, 35723, 35729, 35731,
+    35737, 35753, 35757, 35766, 35773, 35793, 35801, 35807, 35819, 35821, 35832,
+    35835, 35838, 35860, 35885, 35908, 35912, 35918, 35952, 35972, 35975, 35986,
+    36018, 36024, 36025, 36027, 36050, 36054, 36059, 36060, 36061, 36074, 36091,
+    36107, 36121, 36138, 36141, 36148, 36152, 36165, 36187, 36189, 36197, 36204,
+    36212, 36217, 36221, 36230, 36243, 36256, 36260, 36276, 36284, 36309, 36317,
+    36324, 36331, 36346, 36364, 36372, 36378, 36390, 36391, 36397, 36404, 36414,
+    36418, 36435, 36445, 36446, 36447, 36460, 36463, 36474, 36477, 36498, 36533,
+    36544, 36567, 36589, 36590, 36604, 36605, 36608, 36616, 36620, 36621, 36622,
+    36629, 36636, 36639, 36640, 36648, 36649, 36652, 36657, 36684, 36693, 36694,
+    36707, 36726, 36759, 36763, 36764, 36784, 36788, 36800, 36803, 36806, 36814,
+    36824, 36847, 36849, 36865, 36871, 36888, 36912, 36929, 36934, 36952, 36953,
+    36959, 36965, 36976, 36981, 36989, 37004, 37006, 37008, 37012, 37023, 37036,
+    37045, 37065, 37067, 37068, 37078, 37090, 37093, 37096, 37097, 37101, 37113,
+    37132, 37152, 37157, 37163, 37180, 37202, 37206, 37213, 37245, 37251, 37252,
+    37253, 37256, 37257, 37266, 37275, 37286, 37290, 37307, 37315, 37319, 37323,
+    37325, 37338, 37340, 37346, 37360, 37369, 37373, 37377, 37384, 37387, 37402,
+    37407, 37442, 37445, 37451, 37463, 37466, 37473, 37493, 37509, 37521, 37523,
+    37527, 37553, 37571, 37573, 37585, 37589, 37594, 37605, 37611, 37639, 37645,
+    37647, 37656, 37660, 37687, 37688, 37716, 37717, 37719, 37739, 37777, 37811,
+    37818, 37834, 37837, 37841, 37847, 37849, 37857, 37858, 37880, 37881, 37890,
+    37894, 37896, 37905, 37908, 37909, 37927, 37937, 37941, 37943, 37945, 37947,
+    37953, 37961, 37968, 37969, 37995, 38013, 38032, 38056, 38073, 38078, 38099,
+    38120, 38131, 38132, 38150, 38151, 38169, 38182, 38209, 38212, 38221, 38245,
+    38249, 38262, 38267, 38270, 38274, 38290, 38293, 38296, 38301, 38307, 38321,
+    38326, 38328, 38329, 38335, 38340, 38366, 38373, 38375, 38391, 38413, 38416,
+    38422, 38442, 38443, 38460, 38477, 38495, 38500, 38507, 38521, 38522, 38553,
+    38558, 38560, 38580, 38585, 38588, 38604, 38613, 38617, 38637, 38652, 38660,
+    38663, 38666, 38677, 38682, 38684, 38687, 38691, 38702, 38705, 38708, 38709,
+    38715, 38735, 38742, 38750, 38762, 38763, 38777, 38792, 38805, 38811, 38830,
+    38831, 38840, 38879, 38909, 38919, 38921, 38971, 38987, 39005, 39013, 39020,
+    39036, 39050, 39061, 39066, 39073, 39075, 39099, 39123, 39147, 39170, 39191,
+    39206, 39223, 39227, 39234, 39239, 39249, 39261, 39263, 39279, 39285, 39291,
+    39294, 39302, 39310, 39315, 39317, 39336, 39337, 39344, 39361, 39364, 39372,
+    39380, 39384, 39392, 39423, 39442, 39455, 39457, 39459, 39463, 39477, 39483,
+    39486, 39488, 39492, 39501, 39529, 39544, 39548, 39561, 39565, 39582, 39595,
+    39621, 39636, 39667, 39700, 39705, 39738, 39739, 39743, 39747, 39751, 39767,
+    39769, 39787, 39791, 39814, 39817, 39821, 39834, 39839, 39843, 39847, 39857,
+    39869, 39873, 39877, 39892, 39908, 39917, 39921, 39932, 39933, 39934, 39939,
+    39966, 39974, 39975, 39977, 39981, 39984, 39985, 40043, 40065, 40079, 40088,
+    40116, 40132, 40147, 40166, 40183, 40185, 40198, 40199, 40215, 40220, 40228,
+    40232, 40245, 40251, 40272, 40286, 40298, 40305, 40306, 40309, 40329, 40343,
+    40366, 40382, 40385, 40388, 40392, 40410, 40412, 40413, 40418, 40420, 40435,
+    40470, 40477, 40485, 40488, 40516, 40527, 40541, 40543, 40550, 40551, 40591,
+    40603, 40604, 40607, 40613, 40632, 40645, 40646, 40650, 40683, 40690, 40702,
+    40709, 40710, 40742, 40750, 40751, 40753, 40755, 40762, 40764, 40765, 40771,
+    40779, 40781, 40786, 40814, 40827, 40848, 40854, 40857, 40876, 40879, 40888,
+    40903, 40905, 40912, 40930, 40937, 40941, 40964, 40974, 40978, 40980, 40981,
+    41000, 41050, 41062, 41065, 41068, 41070, 41075, 41083, 41090, 41092, 41093,
+    41103, 41135, 41138, 41149, 41150, 41151, 41167, 41169, 41173, 41176, 41185,
+    41189, 41196, 41206, 41217, 41243, 41256, 41261, 41262, 41274, 41279, 41280,
+    41305, 41324, 41361, 41394, 41395, 41405, 41415, 41421, 41430, 41443, 41444,
+    41449, 41467, 41483, 41497, 41510, 41523, 41529, 41543, 41551, 41577, 41605,
+    41608, 41613, 41624, 41628, 41651, 41654, 41655, 41656, 41661, 41673, 41676,
+    41683, 41689, 41703, 41712, 41722, 41738, 41743, 41749, 41761, 41776, 41786,
+    41787, 41801, 41825, 41834, 41838, 41847, 41856, 41858, 41873, 41882, 41894,
+    41900, 41918, 41926, 41935, 41972, 41980, 41982, 41986, 41988, 41990, 42003,
+    42008, 42013, 42015, 42023, 42068, 42070, 42072, 42077, 42113, 42123, 42125,
+    42130, 42137, 42145, 42154, 42162, 42164, 42168, 42172, 42187, 42190, 42194,
+    42198, 42215, 42231, 42240, 42244, 42258, 42259, 42260, 42262, 42263, 42268,
+    42278, 42309, 42325, 42334, 42341, 42347, 42359, 42370, 42376, 42381, 42382,
+    42385, 42392, 42398, 42401, 42402, 42417, 42427, 42433, 42438, 42450, 42455,
+    42467, 42468, 42471, 42472, 42476, 42484, 42488, 42496, 42504, 42515, 42534,
+    42535, 42544, 42545, 42559, 42586, 42593, 42598, 42601, 42637, 42639, 42641,
+    42646, 42649, 42665, 42672, 42678, 42683, 42689, 42706, 42712, 42713, 42718,
+    42739, 42772, 42783, 42796, 42800, 42809, 42810, 42820, 42821, 42825, 42829,
+    42837, 42844, 42845, 42863, 42885, 42898, 42913, 42915, 42929, 42936, 42943,
+    42948, 42952, 42954, 42958, 42961, 42983, 42984, 43004, 43008, 43034, 43035,
+    43048, 43060, 43073, 43074, 43088, 43089, 43099, 43107, 43119, 43135, 43139,
+    43140, 43144, 43152, 43155, 43158, 43160, 43184, 43203, 43205, 43212, 43216,
+    43222, 43227, 43232, 43255, 43269, 43270, 43277, 43280, 43295, 43298, 43310,
+    43318, 43327, 43329, 43331, 43337, 43348, 43352, 43359, 43363, 43364, 43385,
+    43387, 43388, 43398, 43405, 43417, 43420, 43428, 43435, 43447, 43452, 43454,
+    43457, 43482, 43493, 43494, 43501, 43502, 43506, 43517, 43528, 43546, 43567,
+    43571, 43580, 43589, 43614, 43616, 43628, 43636, 43643, 43645, 43662, 43665,
+    43677, 43679, 43690, 43701, 43705, 43723, 43726, 43727, 43775, 43788, 43815,
+    43819, 43831, 43843, 43847, 43849, 43855, 43856, 43863, 43864, 43874, 43886,
+    43904, 43906, 43910, 43911, 43918, 43919, 43925, 43935, 43938, 43955, 43958,
+    43966, 43970, 43971, 43981, 43984, 44005, 44008, 44046, 44047, 44048, 44062,
+    44083, 44090, 44098, 44099, 44111, 44147, 44158, 44172, 44192, 44197, 44208,
+    44209, 44239, 44244, 44251, 44259, 44285, 44294, 44306, 44315, 44326, 44336,
+    44356, 44358, 44372, 44387, 44390, 44408, 44416, 44418, 44422, 44433, 44435,
+    44447, 44448, 44455, 44462, 44473, 44474, 44476, 44484, 44487, 44488, 44490,
+    44495, 44500, 44514, 44516, 44544, 44557, 44562, 44571, 44579, 44598, 44605,
+    44606, 44614, 44621, 44625, 44637, 44648, 44654, 44657, 44663, 44666, 44672,
+    44688, 44692, 44705, 44728, 44734, 44746, 44765, 44766, 44773, 44779, 44806,
+    44824, 44830, 44856, 44868, 44872, 44887, 44898, 44904, 44919, 44927, 44934,
+    44935, 44954, 44955, 44959, 44968, 44970, 44976, 44986, 44990, 44992, 44993,
+    45010, 45026, 45033, 45034, 45036, 45045, 45047, 45054, 45060, 45076, 45079,
+    45103, 45105, 45119, 45122, 45124, 45134, 45135, 45139, 45142, 45143, 45146,
+    45150, 45168, 45194, 45196, 45207, 45231, 45261, 45273, 45275, 45286, 45299,
+    45301, 45311, 45324, 45332, 45340, 45368, 45383, 45390, 45393, 45396, 45400,
+    45413, 45423, 45431, 45443, 45459, 45465, 45479, 45482, 45483, 45512, 45520,
+    45524, 45532, 45537, 45541, 45549, 45563, 45564, 45568, 45569, 45589, 45604,
+    45606, 45611, 45626, 45628, 45634, 45644, 45651, 45671, 45679, 45684, 45685,
+    45696, 45711, 45714, 45730, 45743, 45755, 45757, 45760, 45798, 45801, 45813,
+    45824, 45825, 45829, 45830, 45845, 45846, 45848, 45852, 45854, 45869, 45882,
+    45903, 45904, 45908, 45939, 45944, 45949, 45968, 45978, 45984, 45997, 45998,
+    46009, 46015, 46016, 46026, 46028, 46033, 46053, 46057, 46061, 46065, 46069,
+    46075, 46081, 46087, 46091, 46094, 46112, 46113, 46117, 46121, 46135, 46137,
+    46140, 46142, 46168, 46179, 46206, 46213, 46227, 46239, 46265, 46266, 46272,
+    46277, 46287, 46293, 46300, 46302, 46316, 46324, 46350, 46356, 46368, 46383,
+    46394, 46408, 46413, 46417, 46422, 46435, 46462, 46488, 46490, 46497, 46502,
+    46504, 46505, 46527, 46535, 46551, 46554, 46555, 46571, 46574, 46580, 46583,
+    46599, 46614, 46623, 46626, 46645, 46653, 46660, 46671, 46675, 46696, 46713,
+    46716, 46717, 46718, 46740, 46760, 46796, 46798, 46811, 46812, 46818, 46819,
+    46842, 46848, 46854, 46861, 46862, 46893, 46899, 46903, 46911, 46915, 46922,
+    46923, 46930, 46947, 46952, 46955, 46959, 46979, 46981, 46994, 46998, 47008,
+    47012, 47030, 47033, 47035, 47049, 47052, 47053, 47059, 47062, 47094, 47109,
+    47115, 47121, 47128, 47130, 47140, 47156, 47187, 47189, 47204, 47205, 47211,
+    47215, 47231, 47234, 47235, 47237, 47244, 47256, 47261, 47273, 47304, 47306,
+    47309, 47328, 47334, 47340, 47378, 47380, 47386, 47405, 47419, 47425, 47442,
+    47445, 47450, 47457, 47464, 47465, 47466, 47467, 47477, 47484, 47485, 47488,
+    47494, 47499, 47504, 47518, 47520, 47525, 47533, 47537, 47540, 47545, 47546,
+    47554, 47556, 47566, 47579, 47589, 47598, 47610, 47611, 47614, 47617, 47619,
+    47629, 47658, 47659, 47674, 47683, 47695, 47700, 47707, 47711, 47716, 47727,
+    47738, 47747, 47765, 47769, 47771, 47775, 47783, 47786, 47798, 47801, 47802,
+    47810, 47878, 47910, 47914, 47921, 47924, 47932, 47943, 47953, 47959, 47960,
+    47968, 47971, 47974, 47986, 48009, 48019, 48024, 48037, 48048, 48057, 48060,
+    48076, 48078, 48100, 48126, 48127, 48134, 48142, 48143, 48146, 48153, 48159,
+    48167, 48172, 48204, 48205, 48210, 48231, 48234, 48240, 48254, 48271, 48279,
+    48283, 48299, 48302, 48310, 48315, 48319, 48341, 48353, 48354, 48360, 48362,
+    48383, 48386, 48409, 48427, 48431, 48444, 48447, 48462, 48473, 48474, 48477,
+    48481, 48508, 48518, 48521, 48529, 48534, 48574, 48600, 48610, 48613, 48621,
+    48622, 48625, 48631, 48634, 48639, 48645, 48655, 48670, 48685, 48687, 48690,
+    48691, 48692, 48698, 48709, 48711, 48718, 48727, 48729, 48737, 48759, 48763,
+    48766, 48768, 48776, 48804, 48812, 48819, 48831, 48843, 48848, 48850, 48855,
+    48860, 48878, 48882, 48883, 48905, 48909, 48933, 48934, 48942, 48956, 48957,
+    48964, 48969, 48976, 48978, 48990, 48999, 49003, 49016, 49029, 49031, 49032,
+    49038, 49064, 49078, 49095, 49096, 49101, 49124, 49136, 49140, 49146, 49149,
+    49151, 49155, 49167, 49172, 49183, 49198, 49200, 49203, 49214, 49222, 49232,
+    49240, 49241, 49249, 49250, 49253, 49258, 49264, 49268, 49276, 49280, 49291,
+    49304, 49310, 49315, 49316, 49323, 49344, 49363, 49367, 49371, 49380, 49387,
+    49402, 49417, 49434, 49440, 49444, 49466, 49468, 49490, 49493, 49497, 49501,
+    49518, 49524, 49528, 49547, 49548, 49558, 49565, 49571, 49585, 49591, 49610,
+    49658, 49661, 49702, 49710, 49716, 49727, 49730, 49731, 49747, 49769, 49771,
+    49780, 49783, 49789, 49800, 49805, 49812, 49819, 49827, 49833, 49838, 49847,
+    49853, 49854, 49855, 49870, 49875, 49876, 49879, 49901, 49905, 49911, 49920,
+    49938, 49965, 49973, 49984, 50000, 50010, 50014, 50022, 50024, 50032, 50035,
+    50042, 50045, 50068, 50072, 50082, 50084, 50085, 50098, 50112, 50118, 50126,
+    50141, 50145, 50151, 50155, 50162, 50165, 50167, 50169, 50172, 50181, 50182,
+    50198, 50208, 50210, 50212, 50214, 50228, 50237, 50242, 50247, 50254, 50256,
+    50258, 50358, 50359, 50360, 50361, 50362, 50363, 50365, 50366, 50367, 50368,
+    50369, 50370, 50371, 50372, 50373, 50374, 50375, 50376, 50377, 50378, 50379,
+    50380, 50381, 50382, 50383, 50384, 50385, 50386, 50387, 50388, 50389, 50390,
+    50391, 50392, 50393, 50394, 50395, 50396, 50397, 50398, 50399, 50400, 50401,
+    50402, 50403, 50404, 50405, 50406, 50407, 50408, 50409, 50410, 50411, 50412,
+    50413, 50414, 50415, 50416, 50417, 50418, 50419, 50420, 50421, 50422, 50423,
+    50424, 50425, 50426, 50427, 50428, 50429, 50430, 50431, 50432, 50433, 50434,
+    50435, 50436, 50437, 50438, 50439, 50440, 50441, 50442, 50443, 50444, 50445,
+    50446, 50447, 50448, 50449, 50450, 50451, 50452, 50453, 50454, 50455, 50456,
+    50457, 50458, 50459, 50460, 50461, 50462, 50463, 50464, 50865, 50866, 50867,
+    50868, 50869, 50870, 50871, 50872, 50873, 50874, 50875, 50876, 50877, 50878,
+    50879, 50880, 50881, 50882, 50883, 50884, 50885, 50886, 50887, 50888, 50889,
+    50890, 50891, 50892, 50893, 50894, 50895, 50896, 50897, 50898, 50899, 50900,
+    50901, 50902, 50903, 50904, 50905, 50906, 50907, 50908, 50909, 50910, 50911,
+    50912, 50913, 50914, 50915, 50916, 50917, 50918, 50919, 50920, 50921, 50922,
+    50923, 50924, 50925, 50926, 50927, 50928, 50929, 50930, 50931, 50932, 50933,
+    50934, 50935, 50936, 50937, 50938, 50939, 50940, 50941, 50942, 50943, 50944,
+    50945, 50946, 50947, 50948, 50949, 50950, 50951, 50952, 50953, 50954, 50955,
+    50956, 50957, 50958, 50959, 50960, 50961, 50962, 50963, 50964, 50965, 50966,
+    50967, 50968, 50969, 50970, 50971, 50972, 50973, 50974, 50975, 50976, 50977,
+    50978, 50979, 50980, 50981, 50982, 50983, 50984, 50985, 50986, 50987, 50988,
+    50989, 50990, 50991, 50992, 50993, 50994, 50995, 50996, 50997, 50998, 50999,
+    51000, 51001, 51002, 51003, 51004, 51005, 51006, 51007, 51008, 51009, 51010,
+    51011, 51012, 51013, 51014, 51015, 51016, 51017, 51018, 51019, 51020, 51021,
+    51022, 51023, 51024, 51025, 51026, 51027, 51028, 51029, 51030, 51031, 51032,
+    51033, 51034, 51035, 51036, 51037, 51038, 51039, 51040, 51041, 51042, 51043,
+    51044, 51045, 51046, 51047, 51048, 51049, 51050, 51051, 51052, 51053, 51054,
+    51055, 51056, 51057, 51058, 51059, 51060, 51061, 51062, 51063, 51064, 51065,
+    51066, 51067, 51068, 51069, 51070, 51071, 51072, 51073, 51074, 51075, 51076,
+    51077, 51078, 51079, 51080, 51081, 51082, 51083, 51084, 51085, 51086, 51087,
+    51088, 51089, 51090, 51091, 51092, 51093, 51094, 51095, 51096, 51097, 51098,
+    51099, 51100, 51101, 51102, 51103, 51104, 51105, 51106, 51107, 51108, 51109,
+    51110, 51111, 51112, 51113, 51114, 51115, 51116, 51117, 51118, 51119, 51120,
+    51121, 51122, 51123, 51124, 51125, 51126, 51127, 51128, 51129, 51130, 51131,
+    51132, 51133, 51134, 51135, 51136, 51137, 51138, 51139, 51140, 51141, 51142,
+    51143, 51144, 51145, 51146, 51147, 51148, 51149, 51150, 51151, 51152, 51153,
+    51154, 51155, 51156, 51157, 51158, 51159, 51160, 51161, 51162, 51163, 51164,
+    51165, 51166, 51167, 51168, 51169, 51170, 51171, 51172, 51173, 51174, 51175,
+    51176, 51177, 51178, 51179, 51180, 51181, 51182, 51183, 51184, 51185, 51186,
+    51187, 51188, 51189, 51190, 51191, 51192, 51193, 51194, 51195, 51196, 51197,
+    51198, 51199, 51200, 51201, 51202, 51203, 51204, 51205, 51206, 51207, 51208,
+    51209, 51210, 51211, 51212, 51213, 51214, 51215, 51216, 51217, 51218, 51219,
+    51220, 51221, 51222, 51223, 51224, 51225, 51226, 51227, 51228, 51229, 51230,
+    51231, 51232, 51233, 51234, 51235, 51236, 51237, 51238, 51239, 51240, 51241,
+    51242, 51243, 51244, 51245, 51246, 51247, 51248, 51249, 51250, 51251, 51252,
+    51253, 51254, 51255, 51256, 51257, 51258, 51259, 51260, 51261, 51262, 51263,
+    51264, 51265, 51266, 51267, 51268, 51269, 51270, 51271, 51272, 51273, 51274,
+    51275, 51276, 51277, 51278, 51279, 51280, 51281, 51282, 51283, 51284, 51285,
+    51286, 51287, 51288, 51289, 51290, 51291, 51292, 51293, 51294, 51295, 51296,
+    51297, 51298, 51299, 51300, 51301, 51302, 51303, 51304, 51305, 51306, 51307,
+    51308, 51309, 51310, 51311, 51312, 51313, 51314, 51315, 51316, 51317, 51318,
+    51319, 51320, 51321, 51322, 51323, 51324, 51325, 51326, 51327, 51328, 51329,
+    51330, 51331, 51332, 51333, 51334, 51335, 51336, 51337, 51338, 51339, 51340,
+    51341, 51342, 51343, 51344, 51345, 51346, 51347, 51348, 51349, 51350, 51351,
+    51352, 51353, 51354, 51355, 51356, 51357, 51358, 51359, 51360, 51361, 51362,
+    51363, 51364, 50465, 50466, 50467, 50468, 50469, 50470, 50471, 50472, 50473,
+    50474, 50475, 50476, 50477, 50478, 50479, 50480, 50481, 50482, 50483, 50484,
+    50485, 50486, 50487, 50488, 50489, 50490, 50491, 50492, 50493, 50494, 50495,
+    50496, 50497, 50498, 50499, 50500, 50501, 50502, 50503, 50504, 50505, 50506,
+    50507, 50508, 50509, 50510, 50511, 50512, 50513, 50514, 51365, 51366, 51367,
+    51368, 51369, 51370, 51371, 51372, 51373, 51374, 51375, 51376, 51377, 51378,
+    51379, 51380, 51381, 51382, 51383, 51384, 51385, 51386, 51387, 51388, 51389,
+    51390, 51391, 51392, 51393, 51394, 51395, 51396, 51397, 51398, 51399, 51400,
+    51401, 51402, 51403, 51404, 51405, 51406, 51407, 51408, 51409, 51410, 51411,
+    51412, 51413, 51414, 51415, 51416, 51417, 51418, 51419, 51420, 51421, 51422,
+    51423, 51424, 51425, 51426, 51427, 51428, 51429, 51430, 51431, 51432, 51433,
+    51434, 51435, 51436, 51437, 51438, 51439, 51440, 51441, 51442, 51443, 51444,
+    51445, 51446, 51447, 51448, 51449, 51450, 51451, 51452, 51453, 51454, 51455,
+    51456, 51457, 51458, 51459, 51460, 51461, 51462, 51463, 51464, 51465, 51466,
+    51467, 51468, 51469, 51470, 51471, 51472, 51473, 51474, 51475, 51476, 51477,
+    51478, 51479, 51480, 51481, 51482, 51483, 51484, 51485, 51486, 51487, 51488,
+    51489, 51490, 51491, 51492, 51493, 51494, 51495, 51496, 51497, 51498, 51499,
+    51500, 51501, 51502, 51503, 51504, 51505, 51506, 51507, 51508, 51509, 51510,
+    51511, 51512, 51513, 51514, 51515, 51516, 51517, 51518, 51519, 51520, 51521,
+    51522, 51523, 51524, 51525, 51526, 51527, 51528, 51529, 51530, 51531, 51532,
+    51533, 51534, 51535, 51536, 51537, 51538, 51539, 51540, 51541, 51542, 51543,
+    51544, 51545, 51546, 51547, 51548, 51549, 51550, 51551, 51552, 51553, 51554,
+    51555, 51556, 51557, 51558, 51559, 51560, 51561, 51562, 51563, 51564, 51565,
+    51566, 51567, 51568, 51569, 51570, 51571, 51572, 51573, 51574, 51575, 51576,
+    51577, 51578, 51579, 51580, 51581, 51582, 51583, 51584, 51585, 51586, 51587,
+    51588, 51589, 51590, 51591, 51592, 51593, 51594, 51595, 51596, 51597, 51598,
+    51599, 51600, 51601, 51602, 51603, 51604, 51605, 51606, 51607, 51608, 51609,
+    51610, 51611, 51612, 51613, 51614, 51615, 51616, 51617, 51618, 51619, 51620,
+    51621, 51622, 51623, 51624, 51625, 51626, 51627, 51628, 51629, 51630, 51631,
+    51632, 51633, 51634, 51635, 51636, 51637, 51638, 51639, 51640, 51641, 51642,
+    51643, 51644, 51645, 51646, 51647, 51648, 51649, 51650, 51651, 51652, 51653,
+    51654, 51655, 51656, 51657, 51658, 51659, 51660, 51661, 51662, 51663, 51664,
+    51665, 51666, 51667, 51668, 51669, 51670, 51671, 51672, 51673, 51674, 51675,
+    51676, 51677, 51678, 51679, 51680, 51681, 51682, 51683, 51684, 51685, 51686,
+    51687, 51688, 51689, 51690, 51691, 51692, 51693, 51694, 51695, 51696, 51697,
+    51698, 51699, 51700, 51701, 51702, 51703, 51704, 51705, 51706, 51707, 51708,
+    51709, 51710, 51711, 51712, 51713, 51714, 51715, 51716, 51717, 51718, 51719,
+    51720, 51721, 51722, 51723, 51724, 51725, 51726, 51727, 51728, 51729, 51730,
+    51731, 51732, 51733, 51734, 51735, 51736, 51737, 51738, 51739, 51740, 51741,
+    51742, 51743, 51744, 51745, 51746, 51747, 51748, 51749, 51750, 51751, 51752,
+    51753, 51754, 51755, 51756, 51757, 51758, 51759, 51760, 51761, 51762, 51763,
+    51764, 51765, 51766, 51767, 51768, 51769, 51770, 51771, 51772, 51773, 51774,
+    51775, 51776, 51777, 51778, 51779, 51780, 51781, 51782, 51783, 51784, 51785,
+    51786, 51787, 51788, 51789, 51790, 51791, 51792, 51793, 51794, 51795, 51796,
+    51797, 51798, 51799, 51800, 51801, 51802, 51803, 51804, 51805, 51806, 51807,
+    51808, 51809, 51810, 51811, 51812, 51813, 51814, 51815, 51816, 51817, 51818,
+    51819, 51820, 51821, 51822, 51823, 51824, 51825, 51826, 51827, 51828, 51829,
+    51830, 51831, 51832, 51833, 51834, 51835, 51836, 51837, 51838, 51839, 51840,
+    51841, 51842, 51843, 51844, 51845, 51846, 51847, 51848, 51849, 51850, 51851,
+    51852, 51853, 51854, 51855, 51856, 51857, 51858, 51859, 51860, 51861, 51862,
+    51863, 51864, 50515, 50516, 50517, 50518, 50519, 50520, 50521, 50522, 50523,
+    50524, 50525, 50526, 50527, 50528, 50529, 50530, 50531, 50532, 50533, 50534,
+    50535, 50536, 50537, 50538, 50539, 50540, 50541, 50542, 50543, 50544, 50545,
+    50546, 50547, 50548, 50549, 50550, 50551, 50552, 50553, 50554, 50555, 50556,
+    50557, 50558, 50559, 50560, 50561, 50562, 50563, 50564, 51865, 50565, 50566,
+    50567, 50568, 50569, 50570, 50571, 50572, 50573, 50574, 50575, 50576, 50577,
+    50578, 50579, 50580, 50581, 50582, 50583, 50584, 50585, 50586, 50587, 50588,
+    50589, 50590, 50591, 50592, 50593, 50594, 50595, 50596, 50597, 50598, 50599,
+    50600, 50601, 50602, 50603, 50604, 50605, 50606, 50607, 50608, 50609, 50610,
+    50611, 50612, 50613, 50614, 50615, 50616, 50617, 50618, 50619, 50620, 50621,
+    50622, 50623, 50624, 50625, 50626, 50627, 50628, 50629, 50630, 50631, 50632,
+    50633, 50634, 50635, 50636, 50637, 50638, 50639, 50640, 50641, 50642, 50643,
+    50644, 50645, 50646, 50647, 50648, 50649, 50650, 50651, 50652, 50653, 50654,
+    50655, 50656, 50657, 50658, 50659, 50660, 50661, 50662, 50663, 50664, 50665,
+    50666, 50667, 50668, 50669, 50670, 50671, 50672, 50673, 50674, 50675, 50676,
+    50677, 50678, 50679, 50680, 50681, 50682, 50683, 50684, 50685, 50686, 50687,
+    50688, 50689, 50690, 50691, 50692, 50693, 50694, 50695, 50696, 50697, 50698,
+    50699, 50700, 50701, 50702, 50703, 50704, 50705, 50706, 50707, 50708, 50709,
+    50710, 50711, 50712, 50713, 50714, 50715, 50716, 50717, 50718, 50719, 50720,
+    50721, 50722, 50723, 50724, 50725, 50726, 50727, 50728, 50729, 50730, 50731,
+    50732, 50733, 50734, 50735, 50736, 50737, 50738, 50739, 50740, 50741, 50742,
+    50743, 50744, 50745, 50746, 50747, 50748, 50749, 50750, 50751, 50752, 50753,
+    50754, 50755, 50756, 50757, 50758, 50759, 50760, 50761, 50762, 50763, 50764,
+    50765, 50766, 50767, 50768, 50769, 50770, 50771, 50772, 50773, 50774, 50775,
+    50776, 50777, 50778, 50779, 50780, 50781, 50782, 50783, 50784, 50785, 50786,
+    50787, 50788, 50789, 50790, 50791, 50792, 50793, 50794, 50795, 50796, 50797,
+    50798, 50799, 50800, 50801, 50802, 50803, 50804, 50805, 50806, 50807, 50808,
+    50809, 50810, 50811, 50812, 50813, 50814, 50815, 50816, 50817, 50818, 50819,
+    50820, 50821, 50822, 50823, 50824, 50825, 50826, 50827, 50828, 50829, 50830,
+    50831, 50832, 50833, 50834, 50835, 50836, 50837, 50838, 50839, 50840, 50841,
+    50842, 50843, 50844, 50845, 50846, 50847, 50848, 50849, 50850, 50851, 50852,
+    50853, 50854, 50855, 50856, 50857, 50858, 50859, 50860, 50861, 50862, 50863,
+    50864
+  ],
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "token_ids_to_ignore_for_dtw": [13, 11, 0, 30, 12],
+  "transformers_version": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab370a321fa94ce08d419959813540a4f9b0239b88b2f4207ae28ef6607083c0
+size 3219908024

normalizer.json

@@ -0,0 +1,1742 @@
+{
+  "accessorise": "accessorize",
+  "accessorised": "accessorized",
+  "accessorises": "accessorizes",
+  "accessorising": "accessorizing",
+  "acclimatisation": "acclimatization",
+  "acclimatise": "acclimatize",
+  "acclimatised": "acclimatized",
+  "acclimatises": "acclimatizes",
+  "acclimatising": "acclimatizing",
+  "accoutrements": "accouterments",
+  "aeon": "eon",
+  "aeons": "eons",
+  "aerogramme": "aerogram",
+  "aerogrammes": "aerograms",
+  "aeroplane": "airplane",
+  "aeroplanes": "airplanes",
+  "aesthete": "esthete",
+  "aesthetes": "esthetes",
+  "aesthetic": "esthetic",
+  "aesthetically": "esthetically",
+  "aesthetics": "esthetics",
+  "aetiology": "etiology",
+  "ageing": "aging",
+  "aggrandisement": "aggrandizement",
+  "agonise": "agonize",
+  "agonised": "agonized",
+  "agonises": "agonizes",
+  "agonising": "agonizing",
+  "agonisingly": "agonizingly",
+  "almanack": "almanac",
+  "almanacks": "almanacs",
+  "aluminium": "aluminum",
+  "amortisable": "amortizable",
+  "amortisation": "amortization",
+  "amortisations": "amortizations",
+  "amortise": "amortize",
+  "amortised": "amortized",
+  "amortises": "amortizes",
+  "amortising": "amortizing",
+  "amphitheatre": "amphitheater",
+  "amphitheatres": "amphitheaters",
+  "anaemia": "anemia",
+  "anaemic": "anemic",
+  "anaesthesia": "anesthesia",
+  "anaesthetic": "anesthetic",
+  "anaesthetics": "anesthetics",
+  "anaesthetise": "anesthetize",
+  "anaesthetised": "anesthetized",
+  "anaesthetises": "anesthetizes",
+  "anaesthetising": "anesthetizing",
+  "anaesthetist": "anesthetist",
+  "anaesthetists": "anesthetists",
+  "anaesthetize": "anesthetize",
+  "anaesthetized": "anesthetized",
+  "anaesthetizes": "anesthetizes",
+  "anaesthetizing": "anesthetizing",
+  "analogue": "analog",
+  "analogues": "analogs",
+  "analyse": "analyze",
+  "analysed": "analyzed",
+  "analyses": "analyzes",
+  "analysing": "analyzing",
+  "anglicise": "anglicize",
+  "anglicised": "anglicized",
+  "anglicises": "anglicizes",
+  "anglicising": "anglicizing",
+  "annualised": "annualized",
+  "antagonise": "antagonize",
+  "antagonised": "antagonized",
+  "antagonises": "antagonizes",
+  "antagonising": "antagonizing",
+  "apologise": "apologize",
+  "apologised": "apologized",
+  "apologises": "apologizes",
+  "apologising": "apologizing",
+  "appal": "appall",
+  "appals": "appalls",
+  "appetiser": "appetizer",
+  "appetisers": "appetizers",
+  "appetising": "appetizing",
+  "appetisingly": "appetizingly",
+  "arbour": "arbor",
+  "arbours": "arbors",
+  "archaeologically": "archeologically",
+  "archaeologist": "archeologist",
+  "archaeologists": "archeologists",
+  "archaeology": "archeology</span>",
+  "archeological": "archaeological",
+  "ardour": "ardor",
+  "armour": "armor",
+  "armoured": "armored",
+  "armourer": "armorer",
+  "armourers": "armorers",
+  "armouries": "armories",
+  "armoury": "armory",
+  "artefact": "artifact",
+  "artefacts": "artifacts",
+  "authorise": "authorize",
+  "authorised": "authorized",
+  "authorises": "authorizes",
+  "authorising": "authorizing",
+  "axe": "ax",
+  "backpedalled": "backpedaled",
+  "backpedalling": "backpedaling",
+  "bannister": "banister",
+  "bannisters": "banisters",
+  "baptise": "baptize",
+  "baptised": "baptized",
+  "baptises": "baptizes",
+  "baptising": "baptizing",
+  "bastardise": "bastardize",
+  "bastardised": "bastardized",
+  "bastardises": "bastardizes",
+  "bastardising": "bastardizing",
+  "battleax": "battleaxe",
+  "baulk": "balk",
+  "baulked": "balked",
+  "baulking": "balking",
+  "baulks": "balks",
+  "bedevilled": "bedeviled",
+  "bedevilling": "bedeviling",
+  "behaviour": "behavior",
+  "behavioural": "behavioral",
+  "behaviourism": "behaviorism",
+  "behaviourist": "behaviorist",
+  "behaviourists": "behaviorists",
+  "behaviours": "behaviors",
+  "behove": "behoove",
+  "behoved": "behooved",
+  "behoves": "behooves",
+  "bejewelled": "bejeweled",
+  "belabour": "belabor",
+  "belaboured": "belabored",
+  "belabouring": "belaboring",
+  "belabours": "belabors",
+  "bevelled": "beveled",
+  "bevvies": "bevies",
+  "bevvy": "bevy",
+  "biassed": "biased",
+  "biassing": "biasing",
+  "bingeing": "binging",
+  "bougainvillaea": "bougainvillea",
+  "bougainvillaeas": "bougainvilleas",
+  "bowdlerise": "bowdlerize",
+  "bowdlerised": "bowdlerized",
+  "bowdlerises": "bowdlerizes",
+  "bowdlerising": "bowdlerizing",
+  "breathalyse": "breathalyze",
+  "breathalysed": "breathalyzed",
+  "breathalyser": "breathalyzer",
+  "breathalysers": "breathalyzers",
+  "breathalyses": "breathalyzes",
+  "breathalysing": "breathalyzing",
+  "brutalise": "brutalize",
+  "brutalised": "brutalized",
+  "brutalises": "brutalizes",
+  "brutalising": "brutalizing",
+  "busses": "buses",
+  "bussing": "busing",
+  "caesarean": "cesarean",
+  "caesareans": "cesareans",
+  "calibre": "caliber",
+  "calibres": "calibers",
+  "calliper": "caliper",
+  "callipers": "calipers",
+  "callisthenics": "calisthenics",
+  "canalise": "canalize",
+  "canalised": "canalized",
+  "canalises": "canalizes",
+  "canalising": "canalizing",
+  "cancelation": "cancellation",
+  "cancelations": "cancellations",
+  "cancelled": "canceled",
+  "cancelling": "canceling",
+  "candour": "candor",
+  "cannibalise": "cannibalize",
+  "cannibalised": "cannibalized",
+  "cannibalises": "cannibalizes",
+  "cannibalising": "cannibalizing",
+  "canonise": "canonize",
+  "canonised": "canonized",
+  "canonises": "canonizes",
+  "canonising": "canonizing",
+  "capitalise": "capitalize",
+  "capitalised": "capitalized",
+  "capitalises": "capitalizes",
+  "capitalising": "capitalizing",
+  "caramelise": "caramelize",
+  "caramelised": "caramelized",
+  "caramelises": "caramelizes",
+  "caramelising": "caramelizing",
+  "carbonise": "carbonize",
+  "carbonised": "carbonized",
+  "carbonises": "carbonizes",
+  "carbonising": "carbonizing",
+  "carolled": "caroled",
+  "carolling": "caroling",
+  "catalogue": "catalog",
+  "catalogued": "cataloged",
+  "catalogues": "catalogs",
+  "cataloguing": "cataloging",
+  "catalyse": "catalyze",
+  "catalysed": "catalyzed",
+  "catalyses": "catalyzes",
+  "catalysing": "catalyzing",
+  "categorise": "categorize",
+  "categorised": "categorized",
+  "categorises": "categorizes",
+  "categorising": "categorizing",
+  "cauterise": "cauterize",
+  "cauterised": "cauterized",
+  "cauterises": "cauterizes",
+  "cauterising": "cauterizing",
+  "cavilled": "caviled",
+  "cavilling": "caviling",
+  "centigramme": "centigram",
+  "centigrammes": "centigrams",
+  "centilitre": "centiliter",
+  "centilitres": "centiliters",
+  "centimetre": "centimeter",
+  "centimetres": "centimeters",
+  "centralise": "centralize",
+  "centralised": "centralized",
+  "centralises": "centralizes",
+  "centralising": "centralizing",
+  "centre": "center",
+  "centred": "centered",
+  "centrefold": "centerfold",
+  "centrefolds": "centerfolds",
+  "centrepiece": "centerpiece",
+  "centrepieces": "centerpieces",
+  "centres": "centers",
+  "channelled": "channeled",
+  "channelling": "channeling",
+  "characterise": "characterize",
+  "characterised": "characterized",
+  "characterises": "characterizes",
+  "characterising": "characterizing",
+  "cheque": "check",
+  "chequebook": "checkbook",
+  "chequebooks": "checkbooks",
+  "chequered": "checkered",
+  "cheques": "checks",
+  "chilli": "chili",
+  "chimaera": "chimera",
+  "chimaeras": "chimeras",
+  "chiselled": "chiseled",
+  "chiselling": "chiseling",
+  "circularise": "circularize",
+  "circularised": "circularized",
+  "circularises": "circularizes",
+  "circularising": "circularizing",
+  "civilise": "civilize",
+  "civilised": "civilized",
+  "civilises": "civilizes",
+  "civilising": "civilizing",
+  "clamour": "clamor",
+  "clamoured": "clamored",
+  "clamouring": "clamoring",
+  "clamours": "clamors",
+  "clangour": "clangor",
+  "clarinettist": "clarinetist",
+  "clarinettists": "clarinetists",
+  "collectivise": "collectivize",
+  "collectivised": "collectivized",
+  "collectivises": "collectivizes",
+  "collectivising": "collectivizing",
+  "colonisation": "colonization",
+  "colonise": "colonize",
+  "colonised": "colonized",
+  "coloniser": "colonizer",
+  "colonisers": "colonizers",
+  "colonises": "colonizes",
+  "colonising": "colonizing",
+  "colour": "color",
+  "colourant": "colorant",
+  "colourants": "colorants",
+  "coloured": "colored",
+  "coloureds": "coloreds",
+  "colourful": "colorful",
+  "colourfully": "colorfully",
+  "colouring": "coloring",
+  "colourize": "colorize",
+  "colourized": "colorized",
+  "colourizes": "colorizes",
+  "colourizing": "colorizing",
+  "colourless": "colorless",
+  "colours": "colors",
+  "commercialise": "commercialize",
+  "commercialised": "commercialized",
+  "commercialises": "commercializes",
+  "commercialising": "commercializing",
+  "compartmentalise": "compartmentalize",
+  "compartmentalised": "compartmentalized",
+  "compartmentalises": "compartmentalizes",
+  "compartmentalising": "compartmentalizing",
+  "computerise": "computerize",
+  "computerised": "computerized",
+  "computerises": "computerizes",
+  "computerising": "computerizing",
+  "conceptualise": "conceptualize",
+  "conceptualised": "conceptualized",
+  "conceptualises": "conceptualizes",
+  "conceptualising": "conceptualizing",
+  "connexion": "connection",
+  "connexions": "connections",
+  "contextualise": "contextualize",
+  "contextualised": "contextualized",
+  "contextualises": "contextualizes",
+  "contextualising": "contextualizing",
+  "cosier": "cozier",
+  "cosies": "cozies",
+  "cosiest": "coziest",
+  "cosily": "cozily",
+  "cosiness": "coziness",
+  "cosy": "cozy",
+  "councillor": "councilor",
+  "councillors": "councilors",
+  "counselled": "counseled",
+  "counselling": "counseling",
+  "counsellor": "counselor",
+  "counsellors": "counselors",
+  "crenelated": "crenellated",
+  "criminalise": "criminalize",
+  "criminalised": "criminalized",
+  "criminalises": "criminalizes",
+  "criminalising": "criminalizing",
+  "criticise": "criticize",
+  "criticised": "criticized",
+  "criticises": "criticizes",
+  "criticising": "criticizing",
+  "crueller": "crueler",
+  "cruellest": "cruelest",
+  "crystallisation": "crystallization",
+  "crystallise": "crystallize",
+  "crystallised": "crystallized",
+  "crystallises": "crystallizes",
+  "crystallising": "crystallizing",
+  "cudgelled": "cudgeled",
+  "cudgelling": "cudgeling",
+  "customise": "customize",
+  "customised": "customized",
+  "customises": "customizes",
+  "customising": "customizing",
+  "cypher": "cipher",
+  "cyphers": "ciphers",
+  "decentralisation": "decentralization",
+  "decentralise": "decentralize",
+  "decentralised": "decentralized",
+  "decentralises": "decentralizes",
+  "decentralising": "decentralizing",
+  "decriminalisation": "decriminalization",
+  "decriminalise": "decriminalize",
+  "decriminalised": "decriminalized",
+  "decriminalises": "decriminalizes",
+  "decriminalising": "decriminalizing",
+  "defence": "defense",
+  "defenceless": "defenseless",
+  "defences": "defenses",
+  "dehumanisation": "dehumanization",
+  "dehumanise": "dehumanize",
+  "dehumanised": "dehumanized",
+  "dehumanises": "dehumanizes",
+  "dehumanising": "dehumanizing",
+  "demeanour": "demeanor",
+  "demilitarisation": "demilitarization",
+  "demilitarise": "demilitarize",
+  "demilitarised": "demilitarized",
+  "demilitarises": "demilitarizes",
+  "demilitarising": "demilitarizing",
+  "demobilisation": "demobilization",
+  "demobilise": "demobilize",
+  "demobilised": "demobilized",
+  "demobilises": "demobilizes",
+  "demobilising": "demobilizing",
+  "democratisation": "democratization",
+  "democratise": "democratize",
+  "democratised": "democratized",
+  "democratises": "democratizes",
+  "democratising": "democratizing",
+  "demonise": "demonize",
+  "demonised": "demonized",
+  "demonises": "demonizes",
+  "demonising": "demonizing",
+  "demoralisation": "demoralization",
+  "demoralise": "demoralize",
+  "demoralised": "demoralized",
+  "demoralises": "demoralizes",
+  "demoralising": "demoralizing",
+  "denationalisation": "denationalization",
+  "denationalise": "denationalize",
+  "denationalised": "denationalized",
+  "denationalises": "denationalizes",
+  "denationalising": "denationalizing",
+  "deodorise": "deodorize",
+  "deodorised": "deodorized",
+  "deodorises": "deodorizes",
+  "deodorising": "deodorizing",
+  "depersonalise": "depersonalize",
+  "depersonalised": "depersonalized",
+  "depersonalises": "depersonalizes",
+  "depersonalising": "depersonalizing",
+  "deputise": "deputize",
+  "deputised": "deputized",
+  "deputises": "deputizes",
+  "deputising": "deputizing",
+  "desensitisation": "desensitization",
+  "desensitise": "desensitize",
+  "desensitised": "desensitized",
+  "desensitises": "desensitizes",
+  "desensitising": "desensitizing",
+  "destabilisation": "destabilization",
+  "destabilise": "destabilize",
+  "destabilised": "destabilized",
+  "destabilises": "destabilizes",
+  "destabilising": "destabilizing",
+  "dialled": "dialed",
+  "dialling": "dialing",
+  "dialogue": "dialog",
+  "dialogues": "dialogs",
+  "diarrhoea": "diarrhea",
+  "digitise": "digitize",
+  "digitised": "digitized",
+  "digitises": "digitizes",
+  "digitising": "digitizing",
+  "disc": "disk",
+  "discolour": "discolor",
+  "discoloured": "discolored",
+  "discolouring": "discoloring",
+  "discolours": "discolors",
+  "discs": "disks",
+  "disembowelled": "disemboweled",
+  "disembowelling": "disemboweling",
+  "disfavour": "disfavor",
+  "dishevelled": "disheveled",
+  "dishonour": "dishonor",
+  "dishonourable": "dishonorable",
+  "dishonourably": "dishonorably",
+  "dishonoured": "dishonored",
+  "dishonouring": "dishonoring",
+  "dishonours": "dishonors",
+  "disorganisation": "disorganization",
+  "disorganised": "disorganized",
+  "distil": "distill",
+  "distils": "distills",
+  "dramatisation": "dramatization",
+  "dramatisations": "dramatizations",
+  "dramatise": "dramatize",
+  "dramatised": "dramatized",
+  "dramatises": "dramatizes",
+  "dramatising": "dramatizing",
+  "draught": "draft",
+  "draughtboard": "draftboard",
+  "draughtboards": "draftboards",
+  "draughtier": "draftier",
+  "draughtiest": "draftiest",
+  "draughts": "drafts",
+  "draughtsman": "draftsman",
+  "draughtsmanship": "draftsmanship",
+  "draughtsmen": "draftsmen",
+  "draughtswoman": "draftswoman",
+  "draughtswomen": "draftswomen",
+  "draughty": "drafty",
+  "drivelled": "driveled",
+  "drivelling": "driveling",
+  "duelled": "dueled",
+  "duelling": "dueling",
+  "economise": "economize",
+  "economised": "economized",
+  "economises": "economizes",
+  "economising": "economizing",
+  "editorialise": "editorialize",
+  "editorialised": "editorialized",
+  "editorialises": "editorializes",
+  "editorialising": "editorializing",
+  "edoema": "edema",
+  "empathise": "empathize",
+  "empathised": "empathized",
+  "empathises": "empathizes",
+  "empathising": "empathizing",
+  "emphasise": "emphasize",
+  "emphasised": "emphasized",
+  "emphasises": "emphasizes",
+  "emphasising": "emphasizing",
+  "enamelled": "enameled",
+  "enamelling": "enameling",
+  "enamoured": "enamored",
+  "encyclopaedia": "encyclopedia",
+  "encyclopaedias": "encyclopedias",
+  "encyclopaedic": "encyclopedic",
+  "endeavour": "endeavor",
+  "endeavoured": "endeavored",
+  "endeavouring": "endeavoring",
+  "endeavours": "endeavors",
+  "energise": "energize",
+  "energised": "energized",
+  "energises": "energizes",
+  "energising": "energizing",
+  "enrol": "enroll",
+  "enrols": "enrolls",
+  "enthral": "enthrall",
+  "enthrals": "enthralls",
+  "epaulette": "epaulet",
+  "epaulettes": "epaulets",
+  "epicentre": "epicenter",
+  "epicentres": "epicenters",
+  "epilogue": "epilog",
+  "epilogues": "epilogs",
+  "epitomise": "epitomize",
+  "epitomised": "epitomized",
+  "epitomises": "epitomizes",
+  "epitomising": "epitomizing",
+  "equalisation": "equalization",
+  "equalise": "equalize",
+  "equalised": "equalized",
+  "equaliser": "equalizer",
+  "equalisers": "equalizers",
+  "equalises": "equalizes",
+  "equalising": "equalizing",
+  "eulogise": "eulogize",
+  "eulogised": "eulogized",
+  "eulogises": "eulogizes",
+  "eulogising": "eulogizing",
+  "evangelise": "evangelize",
+  "evangelised": "evangelized",
+  "evangelises": "evangelizes",
+  "evangelising": "evangelizing",
+  "exorcise": "exorcize",
+  "exorcised": "exorcized",
+  "exorcises": "exorcizes",
+  "exorcising": "exorcizing",
+  "extemporisation": "extemporization",
+  "extemporise": "extemporize",
+  "extemporised": "extemporized",
+  "extemporises": "extemporizes",
+  "extemporising": "extemporizing",
+  "externalisation": "externalization",
+  "externalisations": "externalizations",
+  "externalise": "externalize",
+  "externalised": "externalized",
+  "externalises": "externalizes",
+  "externalising": "externalizing",
+  "factorise": "factorize",
+  "factorised": "factorized",
+  "factorises": "factorizes",
+  "factorising": "factorizing",
+  "faecal": "fecal",
+  "faeces": "feces",
+  "familiarisation": "familiarization",
+  "familiarise": "familiarize",
+  "familiarised": "familiarized",
+  "familiarises": "familiarizes",
+  "familiarising": "familiarizing",
+  "fantasise": "fantasize",
+  "fantasised": "fantasized",
+  "fantasises": "fantasizes",
+  "fantasising": "fantasizing",
+  "favour": "favor",
+  "favourable": "favorable",
+  "favourably": "favorably",
+  "favoured": "favored",
+  "favouring": "favoring",
+  "favourite": "favorite",
+  "favourites": "favorites",
+  "favouritism": "favoritism",
+  "favours": "favors",
+  "feminise": "feminize",
+  "feminised": "feminized",
+  "feminises": "feminizes",
+  "feminising": "feminizing",
+  "fertilisation": "fertilization",
+  "fertilise": "fertilize",
+  "fertilised": "fertilized",
+  "fertiliser": "fertilizer",
+  "fertilisers": "fertilizers",
+  "fertilises": "fertilizes",
+  "fertilising": "fertilizing",
+  "fervour": "fervor",
+  "fibre": "fiber",
+  "fibreglass": "fiberglass",
+  "fibres": "fibers",
+  "fictionalisation": "fictionalization",
+  "fictionalisations": "fictionalizations",
+  "fictionalise": "fictionalize",
+  "fictionalised": "fictionalized",
+  "fictionalises": "fictionalizes",
+  "fictionalising": "fictionalizing",
+  "fillet": "filet",
+  "filleted": "fileted",
+  "filleting": "fileting",
+  "fillets": "filets",
+  "finalisation": "finalization",
+  "finalise": "finalize",
+  "finalised": "finalized",
+  "finalises": "finalizes",
+  "finalising": "finalizing",
+  "flautist": "flutist",
+  "flautists": "flutists",
+  "flavour": "flavor",
+  "flavoured": "flavored",
+  "flavouring": "flavoring",
+  "flavourings": "flavorings",
+  "flavourless": "flavorless",
+  "flavours": "flavors",
+  "flavoursome": "flavorsome",
+  "flyer / flier": "flier / flyer",
+  "foetal": "fetal",
+  "foetid": "fetid",
+  "foetus": "fetus",
+  "foetuses": "fetuses",
+  "formalisation": "formalization",
+  "formalise": "formalize",
+  "formalised": "formalized",
+  "formalises": "formalizes",
+  "formalising": "formalizing",
+  "fossilisation": "fossilization",
+  "fossilise": "fossilize",
+  "fossilised": "fossilized",
+  "fossilises": "fossilizes",
+  "fossilising": "fossilizing",
+  "fraternisation": "fraternization",
+  "fraternise": "fraternize",
+  "fraternised": "fraternized",
+  "fraternises": "fraternizes",
+  "fraternising": "fraternizing",
+  "fulfil": "fulfill",
+  "fulfilment": "fulfillment",
+  "fulfils": "fulfills",
+  "funnelled": "funneled",
+  "funnelling": "funneling",
+  "gage": "gauge",
+  "gaged": "gauged",
+  "gages": "gauges",
+  "gaging": "gauging",
+  "galvanise": "galvanize",
+  "galvanised": "galvanized",
+  "galvanises": "galvanizes",
+  "galvanising": "galvanizing",
+  "gambolled": "gamboled",
+  "gambolling": "gamboling",
+  "gaol": "jail",
+  "gaolbird": "jailbird",
+  "gaolbirds": "jailbirds",
+  "gaolbreak": "jailbreak",
+  "gaolbreaks": "jailbreaks",
+  "gaoled": "jailed",
+  "gaoler": "jailer",
+  "gaolers": "jailers",
+  "gaoling": "jailing",
+  "gaols": "jails",
+  "gasses": "gases",
+  "generalisation": "generalization",
+  "generalisations": "generalizations",
+  "generalise": "generalize",
+  "generalised": "generalized",
+  "generalises": "generalizes",
+  "generalising": "generalizing",
+  "ghettoise": "ghettoize",
+  "ghettoised": "ghettoized",
+  "ghettoises": "ghettoizes",
+  "ghettoising": "ghettoizing",
+  "gipsies": "gypsies",
+  "glamor": "glamour",
+  "glamorise": "glamorize",
+  "glamorised": "glamorized",
+  "glamorises": "glamorizes",
+  "glamorising": "glamorizing",
+  "globalisation": "globalization",
+  "globalise": "globalize",
+  "globalised": "globalized",
+  "globalises": "globalizes",
+  "globalising": "globalizing",
+  "glueing": "gluing",
+  "goitre": "goiter",
+  "goitres": "goiters",
+  "gonorrhoea": "gonorrhea",
+  "gramme": "gram",
+  "grammes": "grams",
+  "gravelled": "graveled",
+  "grey": "gray",
+  "greyed": "grayed",
+  "greying": "graying",
+  "greyish": "grayish",
+  "greyness": "grayness",
+  "greys": "grays",
+  "grovelled": "groveled",
+  "grovelling": "groveling",
+  "groyne": "groin",
+  "groynes": "groins",
+  "gruelling": "grueling",
+  "gruellingly": "gruelingly",
+  "gryphon": "griffin",
+  "gryphons": "griffins",
+  "gynaecological": "gynecological",
+  "gynaecologist": "gynecologist",
+  "gynaecologists": "gynecologists",
+  "gynaecology": "gynecology",
+  "haematological": "hematological",
+  "haematologist": "hematologist",
+  "haematologists": "hematologists",
+  "haematology": "hematology",
+  "haemoglobin": "hemoglobin",
+  "haemophilia": "hemophilia",
+  "haemophiliac": "hemophiliac",
+  "haemophiliacs": "hemophiliacs",
+  "haemorrhage": "hemorrhage",
+  "haemorrhaged": "hemorrhaged",
+  "haemorrhages": "hemorrhages",
+  "haemorrhaging": "hemorrhaging",
+  "haemorrhoids": "hemorrhoids",
+  "harbour": "harbor",
+  "harboured": "harbored",
+  "harbouring": "harboring",
+  "harbours": "harbors",
+  "harmonisation": "harmonization",
+  "harmonise": "harmonize",
+  "harmonised": "harmonized",
+  "harmonises": "harmonizes",
+  "harmonising": "harmonizing",
+  "homoeopath": "homeopath",
+  "homoeopathic": "homeopathic",
+  "homoeopaths": "homeopaths",
+  "homoeopathy": "homeopathy",
+  "homogenise": "homogenize",
+  "homogenised": "homogenized",
+  "homogenises": "homogenizes",
+  "homogenising": "homogenizing",
+  "honour": "honor",
+  "honourable": "honorable",
+  "honourably": "honorably",
+  "honoured": "honored",
+  "honouring": "honoring",
+  "honours": "honors",
+  "hospitalisation": "hospitalization",
+  "hospitalise": "hospitalize",
+  "hospitalised": "hospitalized",
+  "hospitalises": "hospitalizes",
+  "hospitalising": "hospitalizing",
+  "humanise": "humanize",
+  "humanised": "humanized",
+  "humanises": "humanizes",
+  "humanising": "humanizing",
+  "humour": "humor",
+  "humoured": "humored",
+  "humouring": "humoring",
+  "humourless": "humorless",
+  "humours": "humors",
+  "hybridise": "hybridize",
+  "hybridised": "hybridized",
+  "hybridises": "hybridizes",
+  "hybridising": "hybridizing",
+  "hypnotise": "hypnotize",
+  "hypnotised": "hypnotized",
+  "hypnotises": "hypnotizes",
+  "hypnotising": "hypnotizing",
+  "hypothesise": "hypothesize",
+  "hypothesised": "hypothesized",
+  "hypothesises": "hypothesizes",
+  "hypothesising": "hypothesizing",
+  "idealisation": "idealization",
+  "idealise": "idealize",
+  "idealised": "idealized",
+  "idealises": "idealizes",
+  "idealising": "idealizing",
+  "idolise": "idolize",
+  "idolised": "idolized",
+  "idolises": "idolizes",
+  "idolising": "idolizing",
+  "immobilisation": "immobilization",
+  "immobilise": "immobilize",
+  "immobilised": "immobilized",
+  "immobiliser": "immobilizer",
+  "immobilisers": "immobilizers",
+  "immobilises": "immobilizes",
+  "immobilising": "immobilizing",
+  "immortalise": "immortalize",
+  "immortalised": "immortalized",
+  "immortalises": "immortalizes",
+  "immortalising": "immortalizing",
+  "immunisation": "immunization",
+  "immunise": "immunize",
+  "immunised": "immunized",
+  "immunises": "immunizes",
+  "immunising": "immunizing",
+  "impanelled": "impaneled",
+  "impanelling": "impaneling",
+  "imperilled": "imperiled",
+  "imperilling": "imperiling",
+  "individualise": "individualize",
+  "individualised": "individualized",
+  "individualises": "individualizes",
+  "individualising": "individualizing",
+  "industrialise": "industrialize",
+  "industrialised": "industrialized",
+  "industrialises": "industrializes",
+  "industrialising": "industrializing",
+  "inflexion": "inflection",
+  "inflexions": "inflections",
+  "initialise": "initialize",
+  "initialised": "initialized",
+  "initialises": "initializes",
+  "initialising": "initializing",
+  "initialled": "initialed",
+  "initialling": "initialing",
+  "instal": "install",
+  "instalment": "installment",
+  "instalments": "installments",
+  "instals": "installs",
+  "instil": "instill",
+  "instils": "instills",
+  "institutionalisation": "institutionalization",
+  "institutionalise": "institutionalize",
+  "institutionalised": "institutionalized",
+  "institutionalises": "institutionalizes",
+  "institutionalising": "institutionalizing",
+  "intellectualise": "intellectualize",
+  "intellectualised": "intellectualized",
+  "intellectualises": "intellectualizes",
+  "intellectualising": "intellectualizing",
+  "internalisation": "internalization",
+  "internalise": "internalize",
+  "internalised": "internalized",
+  "internalises": "internalizes",
+  "internalising": "internalizing",
+  "internationalisation": "internationalization",
+  "internationalise": "internationalize",
+  "internationalised": "internationalized",
+  "internationalises": "internationalizes",
+  "internationalising": "internationalizing",
+  "ionisation": "ionization",
+  "ionise": "ionize",
+  "ionised": "ionized",
+  "ioniser": "ionizer",
+  "ionisers": "ionizers",
+  "ionises": "ionizes",
+  "ionising": "ionizing",
+  "italicise": "italicize",
+  "italicised": "italicized",
+  "italicises": "italicizes",
+  "italicising": "italicizing",
+  "itemise": "itemize",
+  "itemised": "itemized",
+  "itemises": "itemizes",
+  "itemising": "itemizing",
+  "jeopardise": "jeopardize",
+  "jeopardised": "jeopardized",
+  "jeopardises": "jeopardizes",
+  "jeopardising": "jeopardizing",
+  "jewelled": "jeweled",
+  "jeweller": "jeweler",
+  "jewellers": "jewelers",
+  "jewellery": "jewelry",
+  "judgement": "judgment",
+  "kilogramme": "kilogram",
+  "kilogrammes": "kilograms",
+  "kilometre": "kilometer",
+  "kilometres": "kilometers",
+  "labelled": "labeled",
+  "labelling": "labeling",
+  "labour": "labor",
+  "laboured": "labored",
+  "labourer": "laborer",
+  "labourers": "laborers",
+  "labouring": "laboring",
+  "labours": "labors",
+  "lacklustre": "lackluster",
+  "legalisation": "legalization",
+  "legalise": "legalize",
+  "legalised": "legalized",
+  "legalises": "legalizes",
+  "legalising": "legalizing",
+  "legitimise": "legitimize",
+  "legitimised": "legitimized",
+  "legitimises": "legitimizes",
+  "legitimising": "legitimizing",
+  "leukaemia": "leukemia",
+  "levelled": "leveled",
+  "leveller": "leveler",
+  "levellers": "levelers",
+  "levelling": "leveling",
+  "libelled": "libeled",
+  "libelling": "libeling",
+  "libellous": "libelous",
+  "liberalisation": "liberalization",
+  "liberalise": "liberalize",
+  "liberalised": "liberalized",
+  "liberalises": "liberalizes",
+  "liberalising": "liberalizing",
+  "licence": "license",
+  "licenced": "licensed",
+  "licences": "licenses",
+  "licencing": "licensing",
+  "likeable": "likable",
+  "lionisation": "lionization",
+  "lionise": "lionize",
+  "lionised": "lionized",
+  "lionises": "lionizes",
+  "lionising": "lionizing",
+  "liquidise": "liquidize",
+  "liquidised": "liquidized",
+  "liquidiser": "liquidizer",
+  "liquidisers": "liquidizers",
+  "liquidises": "liquidizes",
+  "liquidising": "liquidizing",
+  "litre": "liter",
+  "litres": "liters",
+  "localise": "localize",
+  "localised": "localized",
+  "localises": "localizes",
+  "localising": "localizing",
+  "louvre": "louver",
+  "louvred": "louvered",
+  "louvres": "louvers",
+  "lustre": "luster",
+  "magnetise": "magnetize",
+  "magnetised": "magnetized",
+  "magnetises": "magnetizes",
+  "magnetising": "magnetizing",
+  "manoeuvrability": "maneuverability",
+  "manoeuvrable": "maneuverable",
+  "manoeuvre": "maneuver",
+  "manoeuvred": "maneuvered",
+  "manoeuvres": "maneuvers",
+  "manoeuvring": "maneuvering",
+  "manoeuvrings": "maneuverings",
+  "marginalisation": "marginalization",
+  "marginalise": "marginalize",
+  "marginalised": "marginalized",
+  "marginalises": "marginalizes",
+  "marginalising": "marginalizing",
+  "marshalled": "marshaled",
+  "marshalling": "marshaling",
+  "marvelled": "marveled",
+  "marvelling": "marveling",
+  "marvellous": "marvelous",
+  "marvellously": "marvelously",
+  "materialisation": "materialization",
+  "materialise": "materialize",
+  "materialised": "materialized",
+  "materialises": "materializes",
+  "materialising": "materializing",
+  "maximisation": "maximization",
+  "maximise": "maximize",
+  "maximised": "maximized",
+  "maximises": "maximizes",
+  "maximising": "maximizing",
+  "meagre": "meager",
+  "mechanisation": "mechanization",
+  "mechanise": "mechanize",
+  "mechanised": "mechanized",
+  "mechanises": "mechanizes",
+  "mechanising": "mechanizing",
+  "mediaeval": "medieval",
+  "memorialise": "memorialize",
+  "memorialised": "memorialized",
+  "memorialises": "memorializes",
+  "memorialising": "memorializing",
+  "memorise": "memorize",
+  "memorised": "memorized",
+  "memorises": "memorizes",
+  "memorising": "memorizing",
+  "mesmerise": "mesmerize",
+  "mesmerised": "mesmerized",
+  "mesmerises": "mesmerizes",
+  "mesmerising": "mesmerizing",
+  "metabolise": "metabolize",
+  "metabolised": "metabolized",
+  "metabolises": "metabolizes",
+  "metabolising": "metabolizing",
+  "metre": "meter",
+  "metres": "meters",
+  "mhm": "hmm",
+  "micrometre": "micrometer",
+  "micrometres": "micrometers",
+  "militarise": "militarize",
+  "militarised": "militarized",
+  "militarises": "militarizes",
+  "militarising": "militarizing",
+  "milligramme": "milligram",
+  "milligrammes": "milligrams",
+  "millilitre": "milliliter",
+  "millilitres": "milliliters",
+  "millimetre": "millimeter",
+  "millimetres": "millimeters",
+  "miniaturisation": "miniaturization",
+  "miniaturise": "miniaturize",
+  "miniaturised": "miniaturized",
+  "miniaturises": "miniaturizes",
+  "miniaturising": "miniaturizing",
+  "minibusses": "minibuses",
+  "minimise": "minimize",
+  "minimised": "minimized",
+  "minimises": "minimizes",
+  "minimising": "minimizing",
+  "misbehaviour": "misbehavior",
+  "misdemeanour": "misdemeanor",
+  "misdemeanours": "misdemeanors",
+  "misspelt": "misspelled",
+  "mitre": "miter",
+  "mitres": "miters",
+  "mm": "hmm",
+  "mmm": "hmm",
+  "mobilisation": "mobilization",
+  "mobilise": "mobilize",
+  "mobilised": "mobilized",
+  "mobilises": "mobilizes",
+  "mobilising": "mobilizing",
+  "modelled": "modeled",
+  "modeller": "modeler",
+  "modellers": "modelers",
+  "modelling": "modeling",
+  "modernise": "modernize",
+  "modernised": "modernized",
+  "modernises": "modernizes",
+  "modernising": "modernizing",
+  "moisturise": "moisturize",
+  "moisturised": "moisturized",
+  "moisturiser": "moisturizer",
+  "moisturisers": "moisturizers",
+  "moisturises": "moisturizes",
+  "moisturising": "moisturizing",
+  "monologue": "monolog",
+  "monologues": "monologs",
+  "monopolisation": "monopolization",
+  "monopolise": "monopolize",
+  "monopolised": "monopolized",
+  "monopolises": "monopolizes",
+  "monopolising": "monopolizing",
+  "moralise": "moralize",
+  "moralised": "moralized",
+  "moralises": "moralizes",
+  "moralising": "moralizing",
+  "motorised": "motorized",
+  "mould": "mold",
+  "moulded": "molded",
+  "moulder": "molder",
+  "mouldered": "moldered",
+  "mouldering": "moldering",
+  "moulders": "molders",
+  "mouldier": "moldier",
+  "mouldiest": "moldiest",
+  "moulding": "molding",
+  "mouldings": "moldings",
+  "moulds": "molds",
+  "mouldy": "moldy",
+  "moult": "molt",
+  "moulted": "molted",
+  "moulting": "molting",
+  "moults": "molts",
+  "moustache": "mustache",
+  "moustached": "mustached",
+  "moustaches": "mustaches",
+  "moustachioed": "mustachioed",
+  "multicoloured": "multicolored",
+  "nationalisation": "nationalization",
+  "nationalisations": "nationalizations",
+  "nationalise": "nationalize",
+  "nationalised": "nationalized",
+  "nationalises": "nationalizes",
+  "nationalising": "nationalizing",
+  "naturalisation": "naturalization",
+  "naturalise": "naturalize",
+  "naturalised": "naturalized",
+  "naturalises": "naturalizes",
+  "naturalising": "naturalizing",
+  "neighbour": "neighbor",
+  "neighbourhood": "neighborhood",
+  "neighbourhoods": "neighborhoods",
+  "neighbouring": "neighboring",
+  "neighbourliness": "neighborliness",
+  "neighbourly": "neighborly",
+  "neighbours": "neighbors",
+  "neutralisation": "neutralization",
+  "neutralise": "neutralize",
+  "neutralised": "neutralized",
+  "neutralises": "neutralizes",
+  "neutralising": "neutralizing",
+  "normalisation": "normalization",
+  "normalise": "normalize",
+  "normalised": "normalized",
+  "normalises": "normalizes",
+  "normalising": "normalizing",
+  "odour": "odor",
+  "odourless": "odorless",
+  "odours": "odors",
+  "oesophagus": "esophagus",
+  "oesophaguses": "esophaguses",
+  "oestrogen": "estrogen",
+  "offence": "offense",
+  "offences": "offenses",
+  "omelette": "omelet",
+  "omelettes": "omelets",
+  "optimise": "optimize",
+  "optimised": "optimized",
+  "optimises": "optimizes",
+  "optimising": "optimizing",
+  "organisation": "organization",
+  "organisational": "organizational",
+  "organisations": "organizations",
+  "organise": "organize",
+  "organised": "organized",
+  "organiser": "organizer",
+  "organisers": "organizers",
+  "organises": "organizes",
+  "organising": "organizing",
+  "orthopaedic": "orthopedic",
+  "orthopaedics": "orthopedics",
+  "ostracise": "ostracize",
+  "ostracised": "ostracized",
+  "ostracises": "ostracizes",
+  "ostracising": "ostracizing",
+  "outmanoeuvre": "outmaneuver",
+  "outmanoeuvred": "outmaneuvered",
+  "outmanoeuvres": "outmaneuvers",
+  "outmanoeuvring": "outmaneuvering",
+  "overemphasise": "overemphasize",
+  "overemphasised": "overemphasized",
+  "overemphasises": "overemphasizes",
+  "overemphasising": "overemphasizing",
+  "oxidisation": "oxidization",
+  "oxidise": "oxidize",
+  "oxidised": "oxidized",
+  "oxidises": "oxidizes",
+  "oxidising": "oxidizing",
+  "paederast": "pederast",
+  "paederasts": "pederasts",
+  "paediatric": "pediatric",
+  "paediatrician": "pediatrician",
+  "paediatricians": "pediatricians",
+  "paediatrics": "pediatrics",
+  "paedophile": "pedophile",
+  "paedophiles": "pedophiles",
+  "paedophilia": "pedophilia",
+  "palaeolithic": "paleolithic",
+  "palaeontologist": "paleontologist",
+  "palaeontologists": "paleontologists",
+  "palaeontology": "paleontology",
+  "panelled": "paneled",
+  "panelling": "paneling",
+  "panellist": "panelist",
+  "panellists": "panelists",
+  "paralyse": "paralyze",
+  "paralysed": "paralyzed",
+  "paralyses": "paralyzes",
+  "paralysing": "paralyzing",
+  "parcelled": "parceled",
+  "parcelling": "parceling",
+  "parlour": "parlor",
+  "parlours": "parlors",
+  "particularise": "particularize",
+  "particularised": "particularized",
+  "particularises": "particularizes",
+  "particularising": "particularizing",
+  "passivisation": "passivization",
+  "passivise": "passivize",
+  "passivised": "passivized",
+  "passivises": "passivizes",
+  "passivising": "passivizing",
+  "pasteurisation": "pasteurization",
+  "pasteurise": "pasteurize",
+  "pasteurised": "pasteurized",
+  "pasteurises": "pasteurizes",
+  "pasteurising": "pasteurizing",
+  "patronise": "patronize",
+  "patronised": "patronized",
+  "patronises": "patronizes",
+  "patronising": "patronizing",
+  "patronisingly": "patronizingly",
+  "pedalled": "pedaled",
+  "pedalling": "pedaling",
+  "pedestrianisation": "pedestrianization",
+  "pedestrianise": "pedestrianize",
+  "pedestrianised": "pedestrianized",
+  "pedestrianises": "pedestrianizes",
+  "pedestrianising": "pedestrianizing",
+  "penalise": "penalize",
+  "penalised": "penalized",
+  "penalises": "penalizes",
+  "penalising": "penalizing",
+  "pencilled": "penciled",
+  "pencilling": "penciling",
+  "personalise": "personalize",
+  "personalised": "personalized",
+  "personalises": "personalizes",
+  "personalising": "personalizing",
+  "pharmacopoeia": "pharmacopeia",
+  "pharmacopoeias": "pharmacopeias",
+  "philosophise": "philosophize",
+  "philosophised": "philosophized",
+  "philosophises": "philosophizes",
+  "philosophising": "philosophizing",
+  "philtre": "filter",
+  "philtres": "filters",
+  "phoney": "phony",
+  "plagiarise": "plagiarize",
+  "plagiarised": "plagiarized",
+  "plagiarises": "plagiarizes",
+  "plagiarising": "plagiarizing",
+  "plough": "plow",
+  "ploughed": "plowed",
+  "ploughing": "plowing",
+  "ploughman": "plowman",
+  "ploughmen": "plowmen",
+  "ploughs": "plows",
+  "ploughshare": "plowshare",
+  "ploughshares": "plowshares",
+  "polarisation": "polarization",
+  "polarise": "polarize",
+  "polarised": "polarized",
+  "polarises": "polarizes",
+  "polarising": "polarizing",
+  "politicisation": "politicization",
+  "politicise": "politicize",
+  "politicised": "politicized",
+  "politicises": "politicizes",
+  "politicising": "politicizing",
+  "popularisation": "popularization",
+  "popularise": "popularize",
+  "popularised": "popularized",
+  "popularises": "popularizes",
+  "popularising": "popularizing",
+  "pouffe": "pouf",
+  "pouffes": "poufs",
+  "practise": "practice",
+  "practised": "practiced",
+  "practises": "practices",
+  "practising": "practicing",
+  "praesidium": "presidium",
+  "praesidiums": "presidiums",
+  "pressurisation": "pressurization",
+  "pressurise": "pressurize",
+  "pressurised": "pressurized",
+  "pressurises": "pressurizes",
+  "pressurising": "pressurizing",
+  "pretence": "pretense",
+  "pretences": "pretenses",
+  "primaeval": "primeval",
+  "prioritisation": "prioritization",
+  "prioritise": "prioritize",
+  "prioritised": "prioritized",
+  "prioritises": "prioritizes",
+  "prioritising": "prioritizing",
+  "privatisation": "privatization",
+  "privatisations": "privatizations",
+  "privatise": "privatize",
+  "privatised": "privatized",
+  "privatises": "privatizes",
+  "privatising": "privatizing",
+  "professionalisation": "professionalization",
+  "professionalise": "professionalize",
+  "professionalised": "professionalized",
+  "professionalises": "professionalizes",
+  "professionalising": "professionalizing",
+  "programme": "program",
+  "programmes": "programs",
+  "prologue": "prolog",
+  "prologues": "prologs",
+  "propagandise": "propagandize",
+  "propagandised": "propagandized",
+  "propagandises": "propagandizes",
+  "propagandising": "propagandizing",
+  "proselytise": "proselytize",
+  "proselytised": "proselytized",
+  "proselytiser": "proselytizer",
+  "proselytisers": "proselytizers",
+  "proselytises": "proselytizes",
+  "proselytising": "proselytizing",
+  "psychoanalyse": "psychoanalyze",
+  "psychoanalysed": "psychoanalyzed",
+  "psychoanalyses": "psychoanalyzes",
+  "psychoanalysing": "psychoanalyzing",
+  "publicise": "publicize",
+  "publicised": "publicized",
+  "publicises": "publicizes",
+  "publicising": "publicizing",
+  "pulverisation": "pulverization",
+  "pulverise": "pulverize",
+  "pulverised": "pulverized",
+  "pulverises": "pulverizes",
+  "pulverising": "pulverizing",
+  "pummelled": "pummel",
+  "pummelling": "pummeled",
+  "pyjama": "pajama",
+  "pyjamas": "pajamas",
+  "pzazz": "pizzazz",
+  "quarrelled": "quarreled",
+  "quarrelling": "quarreling",
+  "radicalise": "radicalize",
+  "radicalised": "radicalized",
+  "radicalises": "radicalizes",
+  "radicalising": "radicalizing",
+  "rancour": "rancor",
+  "randomise": "randomize",
+  "randomised": "randomized",
+  "randomises": "randomizes",
+  "randomising": "randomizing",
+  "rationalisation": "rationalization",
+  "rationalisations": "rationalizations",
+  "rationalise": "rationalize",
+  "rationalised": "rationalized",
+  "rationalises": "rationalizes",
+  "rationalising": "rationalizing",
+  "ravelled": "raveled",
+  "ravelling": "raveling",
+  "realisable": "realizable",
+  "realisation": "realization",
+  "realisations": "realizations",
+  "realise": "realize",
+  "realised": "realized",
+  "realises": "realizes",
+  "realising": "realizing",
+  "recognisable": "recognizable",
+  "recognisably": "recognizably",
+  "recognisance": "recognizance",
+  "recognise": "recognize",
+  "recognised": "recognized",
+  "recognises": "recognizes",
+  "recognising": "recognizing",
+  "reconnoitre": "reconnoiter",
+  "reconnoitred": "reconnoitered",
+  "reconnoitres": "reconnoiters",
+  "reconnoitring": "reconnoitering",
+  "refuelled": "refueled",
+  "refuelling": "refueling",
+  "regularisation": "regularization",
+  "regularise": "regularize",
+  "regularised": "regularized",
+  "regularises": "regularizes",
+  "regularising": "regularizing",
+  "remodelled": "remodeled",
+  "remodelling": "remodeling",
+  "remould": "remold",
+  "remoulded": "remolded",
+  "remoulding": "remolding",
+  "remoulds": "remolds",
+  "reorganisation": "reorganization",
+  "reorganisations": "reorganizations",
+  "reorganise": "reorganize",
+  "reorganised": "reorganized",
+  "reorganises": "reorganizes",
+  "reorganising": "reorganizing",
+  "revelled": "reveled",
+  "reveller": "reveler",
+  "revellers": "revelers",
+  "revelling": "reveling",
+  "revitalise": "revitalize",
+  "revitalised": "revitalized",
+  "revitalises": "revitalizes",
+  "revitalising": "revitalizing",
+  "revolutionise": "revolutionize",
+  "revolutionised": "revolutionized",
+  "revolutionises": "revolutionizes",
+  "revolutionising": "revolutionizing",
+  "rhapsodise": "rhapsodize",
+  "rhapsodised": "rhapsodized",
+  "rhapsodises": "rhapsodizes",
+  "rhapsodising": "rhapsodizing",
+  "rigour": "rigor",
+  "rigours": "rigors",
+  "ritualised": "ritualized",
+  "rivalled": "rivaled",
+  "rivalling": "rivaling",
+  "romanticise": "romanticize",
+  "romanticised": "romanticized",
+  "romanticises": "romanticizes",
+  "romanticising": "romanticizing",
+  "rumour": "rumor",
+  "rumoured": "rumored",
+  "rumours": "rumors",
+  "sabre": "saber",
+  "sabres": "sabers",
+  "saltpetre": "saltpeter",
+  "sanitise": "sanitize",
+  "sanitised": "sanitized",
+  "sanitises": "sanitizes",
+  "sanitising": "sanitizing",
+  "satirise": "satirize",
+  "satirised": "satirized",
+  "satirises": "satirizes",
+  "satirising": "satirizing",
+  "saviour": "savior",
+  "saviours": "saviors",
+  "savour": "savor",
+  "savoured": "savored",
+  "savouries": "savories",
+  "savouring": "savoring",
+  "savours": "savors",
+  "savoury": "savory",
+  "scandalise": "scandalize",
+  "scandalised": "scandalized",
+  "scandalises": "scandalizes",
+  "scandalising": "scandalizing",
+  "sceptic": "skeptic",
+  "sceptical": "skeptical",
+  "sceptically": "skeptically",
+  "scepticism": "skepticism",
+  "sceptics": "skeptics",
+  "sceptre": "scepter",
+  "sceptres": "scepters",
+  "scrutinise": "scrutinize",
+  "scrutinised": "scrutinized",
+  "scrutinises": "scrutinizes",
+  "scrutinising": "scrutinizing",
+  "secularisation": "secularization",
+  "secularise": "secularize",
+  "secularised": "secularized",
+  "secularises": "secularizes",
+  "secularising": "secularizing",
+  "sensationalise": "sensationalize",
+  "sensationalised": "sensationalized",
+  "sensationalises": "sensationalizes",
+  "sensationalising": "sensationalizing",
+  "sensitise": "sensitize",
+  "sensitised": "sensitized",
+  "sensitises": "sensitizes",
+  "sensitising": "sensitizing",
+  "sentimentalise": "sentimentalize",
+  "sentimentalised": "sentimentalized",
+  "sentimentalises": "sentimentalizes",
+  "sentimentalising": "sentimentalizing",
+  "sepulchre": "sepulcher",
+  "sepulchres": "sepulchers",
+  "serialisation": "serialization",
+  "serialisations": "serializations",
+  "serialise": "serialize",
+  "serialised": "serialized",
+  "serialises": "serializes",
+  "serialising": "serializing",
+  "sermonise": "sermonize",
+  "sermonised": "sermonized",
+  "sermonises": "sermonizes",
+  "sermonising": "sermonizing",
+  "sheikh": "sheik",
+  "shovelled": "shoveled",
+  "shovelling": "shoveling",
+  "shrivelled": "shriveled",
+  "shrivelling": "shriveling",
+  "signalise": "signalize",
+  "signalised": "signalized",
+  "signalises": "signalizes",
+  "signalising": "signalizing",
+  "signalled": "signaled",
+  "signalling": "signaling",
+  "smoulder": "smolder",
+  "smouldered": "smoldered",
+  "smouldering": "smoldering",
+  "smoulders": "smolders",
+  "snivelled": "sniveled",
+  "snivelling": "sniveling",
+  "snorkelled": "snorkeled",
+  "snorkelling": "snorkeling",
+  "snowplough": "snowplow",
+  "snowploughs": "snowplow",
+  "socialisation": "socialization",
+  "socialise": "socialize",
+  "socialised": "socialized",
+  "socialises": "socializes",
+  "socialising": "socializing",
+  "sodomise": "sodomize",
+  "sodomised": "sodomized",
+  "sodomises": "sodomizes",
+  "sodomising": "sodomizing",
+  "solemnise": "solemnize",
+  "solemnised": "solemnized",
+  "solemnises": "solemnizes",
+  "solemnising": "solemnizing",
+  "sombre": "somber",
+  "specialisation": "specialization",
+  "specialisations": "specializations",
+  "specialise": "specialize",
+  "specialised": "specialized",
+  "specialises": "specializes",
+  "specialising": "specializing",
+  "spectre": "specter",
+  "spectres": "specters",
+  "spiralled": "spiraled",
+  "spiralling": "spiraling",
+  "splendour": "splendor",
+  "splendours": "splendors",
+  "squirrelled": "squirreled",
+  "squirrelling": "squirreling",
+  "stabilisation": "stabilization",
+  "stabilise": "stabilize",
+  "stabilised": "stabilized",
+  "stabiliser": "stabilizer",
+  "stabilisers": "stabilizers",
+  "stabilises": "stabilizes",
+  "stabilising": "stabilizing",
+  "standardisation": "standardization",
+  "standardise": "standardize",
+  "standardised": "standardized",
+  "standardises": "standardizes",
+  "standardising": "standardizing",
+  "stencilled": "stenciled",
+  "stencilling": "stenciling",
+  "sterilisation": "sterilization",
+  "sterilisations": "sterilizations",
+  "sterilise": "sterilize",
+  "sterilised": "sterilized",
+  "steriliser": "sterilizer",
+  "sterilisers": "sterilizers",
+  "sterilises": "sterilizes",
+  "sterilising": "sterilizing",
+  "stigmatisation": "stigmatization",
+  "stigmatise": "stigmatize",
+  "stigmatised": "stigmatized",
+  "stigmatises": "stigmatizes",
+  "stigmatising": "stigmatizing",
+  "storey": "story",
+  "storeys": "stories",
+  "subsidisation": "subsidization",
+  "subsidise": "subsidize",
+  "subsidised": "subsidized",
+  "subsidiser": "subsidizer",
+  "subsidisers": "subsidizers",
+  "subsidises": "subsidizes",
+  "subsidising": "subsidizing",
+  "succour": "succor",
+  "succoured": "succored",
+  "succouring": "succoring",
+  "succours": "succors",
+  "sulphate": "sulfate",
+  "sulphates": "sulfates",
+  "sulphide": "sulfide",
+  "sulphides": "sulfides",
+  "sulphur": "sulfur",
+  "sulphurous": "sulfurous",
+  "summarise": "summarize",
+  "summarised": "summarized",
+  "summarises": "summarizes",
+  "summarising": "summarizing",
+  "swivelled": "swiveled",
+  "swivelling": "swiveling",
+  "symbolise": "symbolize",
+  "symbolised": "symbolized",
+  "symbolises": "symbolizes",
+  "symbolising": "symbolizing",
+  "sympathise": "sympathize",
+  "sympathised": "sympathized",
+  "sympathiser": "sympathizer",
+  "sympathisers": "sympathizers",
+  "sympathises": "sympathizes",
+  "sympathising": "sympathizing",
+  "synchronisation": "synchronization",
+  "synchronise": "synchronize",
+  "synchronised": "synchronized",
+  "synchronises": "synchronizes",
+  "synchronising": "synchronizing",
+  "synthesise": "synthesize",
+  "synthesised": "synthesized",
+  "synthesiser": "synthesizer",
+  "synthesisers": "synthesizers",
+  "synthesises": "synthesizes",
+  "synthesising": "synthesizing",
+  "syphon": "siphon",
+  "syphoned": "siphoned",
+  "syphoning": "siphoning",
+  "syphons": "siphons",
+  "systematisation": "systematization",
+  "systematise": "systematize",
+  "systematised": "systematized",
+  "systematises": "systematizes",
+  "systematising": "systematizing",
+  "tantalise": "tantalize",
+  "tantalised": "tantalized",
+  "tantalises": "tantalizes",
+  "tantalising": "tantalizing",
+  "tantalisingly": "tantalizingly",
+  "tasselled": "tasseled",
+  "technicolour": "technicolor",
+  "temporise": "temporize",
+  "temporised": "temporized",
+  "temporises": "temporizes",
+  "temporising": "temporizing",
+  "tenderise": "tenderize",
+  "tenderised": "tenderized",
+  "tenderises": "tenderizes",
+  "tenderising": "tenderizing",
+  "terrorise": "terrorize",
+  "terrorised": "terrorized",
+  "terrorises": "terrorizes",
+  "terrorising": "terrorizing",
+  "theatre": "theater",
+  "theatregoer": "theatergoer",
+  "theatregoers": "theatergoers",
+  "theatres": "theaters",
+  "theorise": "theorize",
+  "theorised": "theorized",
+  "theorises": "theorizes",
+  "theorising": "theorizing",
+  "tonne": "ton",
+  "tonnes": "tons",
+  "towelled": "toweled",
+  "towelling": "toweling",
+  "toxaemia": "toxemia",
+  "tranquillise": "tranquilize",
+  "tranquillised": "tranquilized",
+  "tranquilliser": "tranquilizer",
+  "tranquillisers": "tranquilizers",
+  "tranquillises": "tranquilizes",
+  "tranquillising": "tranquilizing",
+  "tranquillity": "tranquility",
+  "tranquillize": "tranquilize",
+  "tranquillized": "tranquilized",
+  "tranquillizer": "tranquilizer",
+  "tranquillizers": "tranquilizers",
+  "tranquillizes": "tranquilizes",
+  "tranquillizing": "tranquilizing",
+  "tranquilly": "tranquility",
+  "transistorised": "transistorized",
+  "traumatise": "traumatize",
+  "traumatised": "traumatized",
+  "traumatises": "traumatizes",
+  "traumatising": "traumatizing",
+  "travelled": "traveled",
+  "traveller": "traveler",
+  "travellers": "travelers",
+  "travelling": "traveling",
+  "travelog": "travelogue",
+  "travelogs": "travelogues",
+  "trialled": "trialed",
+  "trialling": "trialing",
+  "tricolour": "tricolor",
+  "tricolours": "tricolors",
+  "trivialise": "trivialize",
+  "trivialised": "trivialized",
+  "trivialises": "trivializes",
+  "trivialising": "trivializing",
+  "tumour": "tumor",
+  "tumours": "tumors",
+  "tunnelled": "tunneled",
+  "tunnelling": "tunneling",
+  "tyrannise": "tyrannize",
+  "tyrannised": "tyrannized",
+  "tyrannises": "tyrannizes",
+  "tyrannising": "tyrannizing",
+  "tyre": "tire",
+  "tyres": "tires",
+  "unauthorised": "unauthorized",
+  "uncivilised": "uncivilized",
+  "underutilised": "underutilized",
+  "unequalled": "unequaled",
+  "unfavourable": "unfavorable",
+  "unfavourably": "unfavorably",
+  "unionisation": "unionization",
+  "unionise": "unionize",
+  "unionised": "unionized",
+  "unionises": "unionizes",
+  "unionising": "unionizing",
+  "unorganised": "unorganized",
+  "unravelled": "unraveled",
+  "unravelling": "unraveling",
+  "unrecognisable": "unrecognizable",
+  "unrecognised": "unrecognized",
+  "unrivalled": "unrivaled",
+  "unsavoury": "unsavory",
+  "untrammelled": "untrammeled",
+  "urbanisation": "urbanization",
+  "urbanise": "urbanize",
+  "urbanised": "urbanized",
+  "urbanises": "urbanizes",
+  "urbanising": "urbanizing",
+  "utilisable": "utilizable",
+  "utilisation": "utilization",
+  "utilise": "utilize",
+  "utilised": "utilized",
+  "utilises": "utilizes",
+  "utilising": "utilizing",
+  "valour": "valor",
+  "vandalise": "vandalize",
+  "vandalised": "vandalized",
+  "vandalises": "vandalizes",
+  "vandalising": "vandalizing",
+  "vaporisation": "vaporization",
+  "vaporise": "vaporize",
+  "vaporised": "vaporized",
+  "vaporises": "vaporizes",
+  "vaporising": "vaporizing",
+  "vapour": "vapor",
+  "vapours": "vapors",
+  "verbalise": "verbalize",
+  "verbalised": "verbalized",
+  "verbalises": "verbalizes",
+  "verbalising": "verbalizing",
+  "victimisation": "victimization",
+  "victimise": "victimize",
+  "victimised": "victimized",
+  "victimises": "victimizes",
+  "victimising": "victimizing",
+  "videodisc": "videodisk",
+  "videodiscs": "videodisks",
+  "vigour": "vigor",
+  "visualisation": "visualization",
+  "visualisations": "visualizations",
+  "visualise": "visualize",
+  "visualised": "visualized",
+  "visualises": "visualizes",
+  "visualising": "visualizing",
+  "vocalisation": "vocalization",
+  "vocalisations": "vocalizations",
+  "vocalise": "vocalize",
+  "vocalised": "vocalized",
+  "vocalises": "vocalizes",
+  "vocalising": "vocalizing",
+  "vulcanised": "vulcanized",
+  "vulgarisation": "vulgarization",
+  "vulgarise": "vulgarize",
+  "vulgarised": "vulgarized",
+  "vulgarises": "vulgarizes",
+  "vulgarising": "vulgarizing",
+  "waggon": "wagon",
+  "waggons": "wagons",
+  "watercolour": "watercolor",
+  "watercolours": "watercolors",
+  "weaselled": "weaseled",
+  "weaselling": "weaseling",
+  "westernisation": "westernization",
+  "westernise": "westernize",
+  "westernised": "westernized",
+  "westernises": "westernizes",
+  "westernising": "westernizing",
+  "womanise": "womanize",
+  "womanised": "womanized",
+  "womaniser": "womanizer",
+  "womanisers": "womanizers",
+  "womanises": "womanizes",
+  "womanising": "womanizing",
+  "woollen": "woolen",
+  "woollens": "woolens",
+  "woollies": "woolies",
+  "woolly": "wooly",
+  "worshipped": "worshiped",
+  "worshipper": "worshiper",
+  "worshipping": "worshiping",
+  "yodelled": "yodeled",
+  "yodelling": "yodeling",
+  "yoghourt": "yogurt",
+  "yoghourts": "yogurts",
+  "yoghurt": "yogurt",
+  "yoghurts": "yogurts"
+}

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,139 @@
+{
+  "additional_special_tokens": [
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|he|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|yue|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nospeech|>",
+    "<|notimestamps|>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.006861437764047724,
+    "train_runtime": 11834.061,
+    "train_samples": 4118364,
+    "train_samples_per_second": 348.009,
+    "train_steps_per_second": 0.272
+}

trainer_state.json

@@ -0,0 +1,798 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.999854310939306,
+  "eval_steps": 5000,
+  "global_step": 3217,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.1751,
+      "step": 25
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.6333333333333335e-06,
+      "loss": 0.1343,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3333333333333336e-06,
+      "loss": 0.1246,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.133333333333334e-06,
+      "loss": 0.1172,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.866666666666667e-06,
+      "loss": 0.1133,
+      "step": 125
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.566666666666667e-06,
+      "loss": 0.1104,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 5.366666666666666e-06,
+      "loss": 0.1098,
+      "step": 175
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 6.1e-06,
+      "loss": 0.1077,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 6.833333333333334e-06,
+      "loss": 0.1061,
+      "step": 225
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 7.566666666666667e-06,
+      "loss": 0.1068,
+      "step": 250
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.3e-06,
+      "loss": 0.1074,
+      "step": 275
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.033333333333334e-06,
+      "loss": 0.107,
+      "step": 300
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 0.1048,
+      "step": 325
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.941720946177581e-06,
+      "loss": 0.1062,
+      "step": 350
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.862872814535483e-06,
+      "loss": 0.1061,
+      "step": 375
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.787452862529997e-06,
+      "loss": 0.1051,
+      "step": 400
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.7086047308879e-06,
+      "loss": 0.1056,
+      "step": 425
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.633184778882414e-06,
+      "loss": 0.1045,
+      "step": 450
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.554336647240316e-06,
+      "loss": 0.1042,
+      "step": 475
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.475488515598218e-06,
+      "loss": 0.105,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.39664038395612e-06,
+      "loss": 0.104,
+      "step": 525
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.321220431950634e-06,
+      "loss": 0.104,
+      "step": 550
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.242372300308537e-06,
+      "loss": 0.1017,
+      "step": 575
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.166952348303052e-06,
+      "loss": 0.104,
+      "step": 600
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.088104216660953e-06,
+      "loss": 0.1021,
+      "step": 625
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.012684264655469e-06,
+      "loss": 0.1027,
+      "step": 650
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 8.940692492286596e-06,
+      "loss": 0.1041,
+      "step": 675
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 8.861844360644498e-06,
+      "loss": 0.1022,
+      "step": 700
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 8.789852588275626e-06,
+      "loss": 0.1021,
+      "step": 725
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 8.711004456633528e-06,
+      "loss": 0.103,
+      "step": 750
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 8.63215632499143e-06,
+      "loss": 0.1033,
+      "step": 775
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 8.560164552622558e-06,
+      "loss": 0.1036,
+      "step": 800
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.484744600617072e-06,
+      "loss": 0.101,
+      "step": 825
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 8.409324648611588e-06,
+      "loss": 0.1022,
+      "step": 850
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 8.34076105587933e-06,
+      "loss": 0.1014,
+      "step": 875
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 8.265341103873843e-06,
+      "loss": 0.1005,
+      "step": 900
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 8.186492972231745e-06,
+      "loss": 0.0999,
+      "step": 925
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.114501199862873e-06,
+      "loss": 0.0993,
+      "step": 950
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.042509427494002e-06,
+      "loss": 0.1017,
+      "step": 975
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 7.97051765512513e-06,
+      "loss": 0.0997,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 7.895097703119644e-06,
+      "loss": 0.1004,
+      "step": 1025
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.812821391840933e-06,
+      "loss": 0.1005,
+      "step": 1050
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 7.737401439835449e-06,
+      "loss": 0.0996,
+      "step": 1075
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 7.661981487829963e-06,
+      "loss": 0.1,
+      "step": 1100
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 7.589989715461091e-06,
+      "loss": 0.0994,
+      "step": 1125
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 7.5111415838189925e-06,
+      "loss": 0.0995,
+      "step": 1150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.43914981145012e-06,
+      "loss": 0.1004,
+      "step": 1175
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.363729859444636e-06,
+      "loss": 0.1011,
+      "step": 1200
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.2814535481659246e-06,
+      "loss": 0.1002,
+      "step": 1225
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.209461775797052e-06,
+      "loss": 0.099,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 7.137470003428181e-06,
+      "loss": 0.0996,
+      "step": 1275
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 7.058621871786082e-06,
+      "loss": 0.1,
+      "step": 1300
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 6.983201919780597e-06,
+      "loss": 0.0992,
+      "step": 1325
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 6.904353788138499e-06,
+      "loss": 0.0993,
+      "step": 1350
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 6.825505656496401e-06,
+      "loss": 0.0975,
+      "step": 1375
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.756942063764142e-06,
+      "loss": 0.097,
+      "step": 1400
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 6.68495029139527e-06,
+      "loss": 0.0988,
+      "step": 1425
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 6.612958519026398e-06,
+      "loss": 0.096,
+      "step": 1450
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 6.537538567020913e-06,
+      "loss": 0.0972,
+      "step": 1475
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 6.462118615015427e-06,
+      "loss": 0.0978,
+      "step": 1500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 6.386698663009943e-06,
+      "loss": 0.0985,
+      "step": 1525
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 6.3044223517312304e-06,
+      "loss": 0.0982,
+      "step": 1550
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 6.235858758998972e-06,
+      "loss": 0.098,
+      "step": 1575
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.1638669866301e-06,
+      "loss": 0.0965,
+      "step": 1600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.091875214261228e-06,
+      "loss": 0.0963,
+      "step": 1625
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.01302708261913e-06,
+      "loss": 0.097,
+      "step": 1650
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 5.937607130613645e-06,
+      "loss": 0.0972,
+      "step": 1675
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 5.86218717860816e-06,
+      "loss": 0.0977,
+      "step": 1700
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.783339046966061e-06,
+      "loss": 0.0971,
+      "step": 1725
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.71134727459719e-06,
+      "loss": 0.0965,
+      "step": 1750
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.632499142955091e-06,
+      "loss": 0.0971,
+      "step": 1775
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.557079190949606e-06,
+      "loss": 0.0967,
+      "step": 1800
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.485087418580734e-06,
+      "loss": 0.0949,
+      "step": 1825
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.413095646211862e-06,
+      "loss": 0.0968,
+      "step": 1850
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.337675694206377e-06,
+      "loss": 0.0974,
+      "step": 1875
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 5.269112101474117e-06,
+      "loss": 0.0952,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 5.193692149468632e-06,
+      "loss": 0.0952,
+      "step": 1925
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 5.118272197463148e-06,
+      "loss": 0.0967,
+      "step": 1950
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 5.0462804250942755e-06,
+      "loss": 0.0948,
+      "step": 1975
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.9708604730887904e-06,
+      "loss": 0.0967,
+      "step": 2000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.892012341446693e-06,
+      "loss": 0.0953,
+      "step": 2025
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.82002056907782e-06,
+      "loss": 0.0951,
+      "step": 2050
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.737744257799109e-06,
+      "loss": 0.0952,
+      "step": 2075
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.662324305793624e-06,
+      "loss": 0.0962,
+      "step": 2100
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.586904353788139e-06,
+      "loss": 0.0953,
+      "step": 2125
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.51834076105588e-06,
+      "loss": 0.0942,
+      "step": 2150
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.439492629413782e-06,
+      "loss": 0.0943,
+      "step": 2175
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.360644497771684e-06,
+      "loss": 0.1057,
+      "step": 2200
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.288652725402811e-06,
+      "loss": 0.1048,
+      "step": 2225
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.216660953033939e-06,
+      "loss": 0.1063,
+      "step": 2250
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.144669180665067e-06,
+      "loss": 0.1051,
+      "step": 2275
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.069249228659582e-06,
+      "loss": 0.104,
+      "step": 2300
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.990401097017484e-06,
+      "loss": 0.1064,
+      "step": 2325
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.914981145011999e-06,
+      "loss": 0.1038,
+      "step": 2350
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.84641755227974e-06,
+      "loss": 0.1038,
+      "step": 2375
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.764141241001029e-06,
+      "loss": 0.1028,
+      "step": 2400
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.6887212889955437e-06,
+      "loss": 0.1044,
+      "step": 2425
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.6167295166266713e-06,
+      "loss": 0.1052,
+      "step": 2450
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.5413095646211863e-06,
+      "loss": 0.1042,
+      "step": 2475
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.4693177922523143e-06,
+      "loss": 0.104,
+      "step": 2500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.3973260198834423e-06,
+      "loss": 0.1025,
+      "step": 2525
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.321906067877957e-06,
+      "loss": 0.1031,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.2430579362358587e-06,
+      "loss": 0.1049,
+      "step": 2575
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.164209804593761e-06,
+      "loss": 0.1039,
+      "step": 2600
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.088789852588276e-06,
+      "loss": 0.1032,
+      "step": 2625
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.0167980802194034e-06,
+      "loss": 0.1032,
+      "step": 2650
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.9413781282139188e-06,
+      "loss": 0.1036,
+      "step": 2675
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.8625299965718206e-06,
+      "loss": 0.1027,
+      "step": 2700
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.7836818649297224e-06,
+      "loss": 0.1016,
+      "step": 2725
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.7082619129242378e-06,
+      "loss": 0.1035,
+      "step": 2750
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.6294137812821396e-06,
+      "loss": 0.1025,
+      "step": 2775
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.557422008913267e-06,
+      "loss": 0.1013,
+      "step": 2800
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.471717517997943e-06,
+      "loss": 0.1026,
+      "step": 2825
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.3997257456290712e-06,
+      "loss": 0.1026,
+      "step": 2850
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.331162152896812e-06,
+      "loss": 0.1019,
+      "step": 2875
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.252314021254714e-06,
+      "loss": 0.101,
+      "step": 2900
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.183750428522455e-06,
+      "loss": 0.1026,
+      "step": 2925
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.1083304765169694e-06,
+      "loss": 0.1014,
+      "step": 2950
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.0363387041480975e-06,
+      "loss": 0.1022,
+      "step": 2975
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.9574905725059997e-06,
+      "loss": 0.1015,
+      "step": 3000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8786424408639015e-06,
+      "loss": 0.1029,
+      "step": 3025
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.8066506684950293e-06,
+      "loss": 0.1022,
+      "step": 3050
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.7312307164895443e-06,
+      "loss": 0.1014,
+      "step": 3075
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.6523825848474463e-06,
+      "loss": 0.1002,
+      "step": 3100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.573534453205348e-06,
+      "loss": 0.1017,
+      "step": 3125
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.504970860473089e-06,
+      "loss": 0.1015,
+      "step": 3150
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.4226945491943777e-06,
+      "loss": 0.101,
+      "step": 3175
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3541309564621189e-06,
+      "loss": 0.1017,
+      "step": 3200
+    },
+    {
+      "epoch": 1.0,
+      "step": 3217,
+      "total_flos": 1.3990082808835046e+22,
+      "train_loss": 0.006861437764047724,
+      "train_runtime": 11834.061,
+      "train_samples_per_second": 348.009,
+      "train_steps_per_second": 0.272
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3217,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "total_flos": 1.3990082808835046e+22,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b4a87e935a72c4ad19940265a06cfcd003c0f653392960b6d96d369c47ae8d
+size 26552

transcribe.py

@@ -0,0 +1,56 @@
+import argparse
+import os
+import sys
+import torch
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
+
+
+def transcribe_audio(file_path):
+    device = "cuda:0" if torch.cuda.is_available() else "cpu"
+    torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+
+    model_id = "nyrahealth/CrisperWhisper"  # You can change this to a different model if needed
+
+    model = AutoModelForSpeechSeq2Seq.from_pretrained(
+        model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
+    )
+    model.to(device)
+
+    processor = AutoProcessor.from_pretrained(model_id)
+
+    pipe = pipeline(
+        "automatic-speech-recognition",
+        model=model,
+        tokenizer=processor.tokenizer,
+        feature_extractor=processor.feature_extractor,
+        chunk_length_s=30,
+        batch_size=16,
+        return_timestamps="word",
+        torch_dtype=torch_dtype,
+        device=device,
+    )
+
+    result = pipe(file_path)
+    return result
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Transcribe an audio file.")
+    parser.add_argument("--f", type=str, required=True, help="Path to the audio file")
+    args = parser.parse_args()
+
+    if not os.path.exists(args.f):
+        print(f"Error: The file '{args.f}' does not exist.")
+        sys.exit(1)
+
+    try:
+        transcription = transcribe_audio(args.f)
+        print("Transcription:")
+        print(transcription["text"])
+    except Exception as e:
+        print(f"An error occurred while transcribing the audio: {str(e)}")
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

utils.py

@@ -0,0 +1,29 @@
+def adjust_pauses_for_hf_pipeline_output(pipeline_output, split_threshold=0.12):
+    """
+    Adjust pause timings by distributing pauses up to the threshold evenly between adjacent words.
+    """
+
+    adjusted_chunks = pipeline_output["chunks"].copy()
+
+    for i in range(len(adjusted_chunks) - 1):
+        current_chunk = adjusted_chunks[i]
+        next_chunk = adjusted_chunks[i + 1]
+
+        current_start, current_end = current_chunk["timestamp"]
+        next_start, next_end = next_chunk["timestamp"]
+        pause_duration = next_start - current_end
+
+        if pause_duration > 0:
+            if pause_duration > split_threshold:
+                distribute = split_threshold / 2
+            else:
+                distribute = pause_duration / 2
+
+            # Adjust current chunk end time
+            adjusted_chunks[i]["timestamp"] = (current_start, current_end + distribute)
+
+            # Adjust next chunk start time
+            adjusted_chunks[i + 1]["timestamp"] = (next_start - distribute, next_end)
+    pipeline_output["chunks"] = adjusted_chunks
+
+    return pipeline_output