Updating to remove spaces before punctuation (#4)

- Update model and readme to remove space before punctuation (41d1523404c4cb6e3bbb850b8e299ff4a58cae12)


Co-authored-by: Igor Gitman <igitman@users.noreply.huggingface.co>

README.md

@@ -35,7 +35,7 @@ model-index:
     metrics:
     - name: Test WER
       type: wer
-      value: 5.77
+      value: 5.67
   - task:
       type: Automatic Speech Recognition
       name: automatic-speech-recognition
@@ -49,7 +49,7 @@ model-index:
     metrics:
     - name: Test WER
       type: wer
-      value: 11.47
+      value: 11.11
   - task:
       type: Automatic Speech Recognition
       name: speech-recognition
@@ -63,7 +63,7 @@ model-index:
     metrics:
     - name: Test WER
       type: wer
-      value: 15.60
+      value: 16.16
   - task:
       type: Automatic Speech Recognition
       name: speech-recognition
@@ -77,7 +77,7 @@ model-index:
     metrics:
     - name: Test WER P&C
       type: wer
-      value: 8.17
+      value: 8.14
   - task:
       type: Automatic Speech Recognition
       name: automatic-speech-recognition
@@ -91,7 +91,7 @@ model-index:
     metrics:
     - name: Test WER P&C
       type: wer
-      value: 22.48
+      value: 22.06
   - task:
       type: Automatic Speech Recognition
       name: speech-recognition
@@ -105,7 +105,7 @@ model-index:
     metrics:
     - name: Test WER P&C
       type: wer
-      value: 19.55    
+      value: 19.96
 ---
 # NVIDIA FastConformer-Hybrid Large (it)
 
@@ -129,7 +129,7 @@ See the [model architecture](#model-architecture) section and [NeMo documentatio
 To train, fine-tune or play with the model you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed latest Pytorch version.
 ```
 pip install nemo_toolkit['all']
-``` 
+```
 
 ## How to Use this Model
 
@@ -156,15 +156,15 @@ asr_model.transcribe(['2086-149220-0033.wav'])
 
 Using Transducer mode inference:
 ```shell
-python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py 
- pretrained_name="nvidia/stt_it_fastconformer_hybrid_large_pc" 
+python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
+ pretrained_name="nvidia/stt_it_fastconformer_hybrid_large_pc"
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
 ```
 
 Using CTC mode inference:
 ```shell
-python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py 
- pretrained_name="nvidia/stt_it_fastconformer_hybrid_large_pc" 
+python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
+ pretrained_name="nvidia/stt_it_fastconformer_hybrid_large_pc"
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
  decoder_type="ctc"
 ```
@@ -199,21 +199,21 @@ The model in this collection are trained on a composite dataset (NeMo PnC IT ASR
 
 The performance of Automatic Speech Recognition models is measuring using Word Error Rate. Since this dataset is trained on multiple domains and a much larger corpus, it will generally perform better at transcribing audio in general.
 
-The following tables summarizes the performance of the available models in this collection with the Transducer decoder. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding. 
+The following tables summarizes the performance of the available models in this collection with the Transducer decoder. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.
 
 
 a) On data without Punctuation and Capitalization
 
 | Version | Tokenizer             | Vocabulary Size | MCV 12.0 Dev | MCV 12.0 Test | MLS Dev | MLS Test | VoxPopuli Dev | VoxPopuli Test |
 |---------|-----------------------|-----------------|--------------|---------------|---------|----------|---------------|----------------|
-| 1.18.0  | SentencePiece Unigram | 1024            | 5.14%        | 5.68%         | 13.83%  | 11.71%   | 12.80%        | 15.72%         |
+| 1.20.0  | SentencePiece BPE     | 512             | 5.13%        | 5.67%         | 13.16%  | 11.11%   | 12.92%        | 16.16%         |
 
 
 b) On data with Punctuation and Capitalization
 
 | Version | Tokenizer             | Vocabulary Size | MCV 12.0 Dev | MCV 12.0 Test | MLS Dev | MLS Test | VoxPopuli Dev | VoxPopuli Test |
 |---------|-----------------------|-----------------|--------------|---------------|---------|----------|---------------|----------------|
-| 1.18.0  | SentencePiece Unigram | 1024            | 7.75%        | 8.17%         | 26.37%  | 22.48%   | 16.78%        | 19.55%         |
+| 1.20.0  | SentencePiece BPE     | 512             | 7.66%        | 8.14%         | 26.48%  | 22.06%   | 16.91%        | 19.96%         |
 
 
 ## Limitations
@@ -221,15 +221,15 @@ Since this model was trained on publically available speech datasets, the perfor
 
 ## NVIDIA Riva: Deployment
 
-[NVIDIA Riva](https://developer.nvidia.com/riva), is an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, on edge, and embedded. 
-Additionally, Riva provides: 
+[NVIDIA Riva](https://developer.nvidia.com/riva), is an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, on edge, and embedded.
+Additionally, Riva provides:
 
-* World-class out-of-the-box accuracy for the most common languages with model checkpoints trained on proprietary data with hundreds of thousands of GPU-compute hours 
-* Best in class accuracy with run-time word boosting (e.g., brand and product names) and customization of acoustic model, language model, and inverse text normalization 
-* Streaming speech recognition, Kubernetes compatible scaling, and enterprise-grade support 
+* World-class out-of-the-box accuracy for the most common languages with model checkpoints trained on proprietary data with hundreds of thousands of GPU-compute hours
+* Best in class accuracy with run-time word boosting (e.g., brand and product names) and customization of acoustic model, language model, and inverse text normalization
+* Streaming speech recognition, Kubernetes compatible scaling, and enterprise-grade support
 
-Although this model isn’t supported yet by Riva, the [list of supported models is here](https://huggingface.co/models?other=Riva).  
-Check out [Riva live demo](https://developer.nvidia.com/riva#demos). 
+Although this model isn’t supported yet by Riva, the [list of supported models is here](https://huggingface.co/models?other=Riva).
+Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
 
 ## References
 [1] [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://arxiv.org/abs/2305.05084)
@@ -240,4 +240,4 @@ Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
 
 ## Licence
 
-License to use this model is covered by the [CC-BY-4 License](https://creativecommons.org/licenses/by/4.0/legalcode) unless another License/Terms Of Use/EULA is clearly specified. By downloading the public and release version of the model, you accept the terms and conditions of the [CC-BY-4 License](https://creativecommons.org/licenses/by/4.0/legalcode).
+License to use this model is covered by the [CC-BY-4 License](https://creativecommons.org/licenses/by/4.0/legalcode) unless another License/Terms Of Use/EULA is clearly specified. By downloading the public and release version of the model, you accept the terms and conditions of the [CC-BY-4 License](https://creativecommons.org/licenses/by/4.0/legalcode).

stt_it_fastconformer_hybrid_large_pc.nemo

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54b843c8c5da2301a689a7e586ea1ff270655aa6d4e0ed1174e1ff041a7c6c56
-size 459223040
+oid sha256:1bf97c6b148d20c10dea8f950da3359244c7fb9681994153e41cda8c276e77ea
+size 455505920