Commit
•
2175f23
1
Parent(s):
005e305
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice_11_0
|
| 7 |
+
metrics:
|
| 8 |
+
- wer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: whisper-large-zh-cv11
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Automatic Speech Recognition
|
| 14 |
+
type: automatic-speech-recognition
|
| 15 |
+
dataset:
|
| 16 |
+
name: common_voice_11_0
|
| 17 |
+
type: common_voice_11_0
|
| 18 |
+
config: zh-CN
|
| 19 |
+
split: validation[:1000]
|
| 20 |
+
args: zh-CN
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Wer
|
| 23 |
+
type: wer
|
| 24 |
+
value: 52.307692307692314
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# whisper-large-zh-cv11
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_11_0 dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.2501
|
| 35 |
+
- Wer: 52.3077
|
| 36 |
+
- Cer: 8.9573
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 5e-06
|
| 56 |
+
- train_batch_size: 16
|
| 57 |
+
- eval_batch_size: 8
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 2
|
| 60 |
+
- total_train_batch_size: 32
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_steps: 2000
|
| 64 |
+
- training_steps: 20000
|
| 65 |
+
- mixed_precision_training: Native AMP
|
| 66 |
+
|
| 67 |
+
### Training results
|
| 68 |
+
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 70 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
|
| 71 |
+
| 0.3314 | 0.83 | 1000 | 0.2110 | 65.7014 | 10.8047 |
|
| 72 |
+
| 0.2747 | 1.66 | 2000 | 0.2005 | 58.1900 | 9.4191 |
|
| 73 |
+
| 0.1989 | 2.49 | 3000 | 0.1983 | 56.1991 | 9.0939 |
|
| 74 |
+
| 0.1142 | 3.31 | 4000 | 0.2076 | 55.0226 | 9.1589 |
|
| 75 |
+
| 0.0747 | 4.14 | 5000 | 0.2131 | 56.3801 | 9.0483 |
|
| 76 |
+
| 0.0709 | 4.97 | 6000 | 0.2165 | 54.6606 | 8.9768 |
|
| 77 |
+
| 0.0432 | 5.8 | 7000 | 0.2222 | 54.0271 | 8.9508 |
|
| 78 |
+
| 0.0261 | 6.63 | 8000 | 0.2299 | 54.4796 | 9.0353 |
|
| 79 |
+
| 0.0152 | 7.46 | 9000 | 0.2290 | 52.7602 | 8.8076 |
|
| 80 |
+
| 0.0054 | 8.28 | 10000 | 0.2435 | 51.6742 | 8.5279 |
|
| 81 |
+
| 0.0028 | 9.11 | 11000 | 0.2421 | 53.0317 | 8.9833 |
|
| 82 |
+
| 0.0045 | 9.94 | 12000 | 0.2462 | 52.9412 | 8.7751 |
|
| 83 |
+
| 0.0016 | 10.77 | 13000 | 0.2501 | 52.3077 | 8.9573 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.26.0.dev0
|
| 89 |
+
- Pytorch 1.13.1+cu117
|
| 90 |
+
- Datasets 2.7.1.dev0
|
| 91 |
+
- Tokenizers 0.13.2
|