update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: openai/whisper-large-v2
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# openai/whisper-large-v2
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2284
|
| 20 |
+
- Wer: 7.6453
|
| 21 |
+
- Cer: 4.7187
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 16
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 500
|
| 49 |
+
- training_steps: 10000
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 55 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|
|
| 56 |
+
| 0.1912 | 0.55 | 1000 | 0.1828 | 11.2314 | 7.0357 |
|
| 57 |
+
| 0.1329 | 1.1 | 2000 | 0.1618 | 9.4172 | 5.9028 |
|
| 58 |
+
| 0.0912 | 1.65 | 3000 | 0.1616 | 8.9257 | 5.4711 |
|
| 59 |
+
| 0.0576 | 2.2 | 4000 | 0.1664 | 8.5861 | 5.3055 |
|
| 60 |
+
| 0.0449 | 2.74 | 5000 | 0.1642 | 8.4510 | 5.2930 |
|
| 61 |
+
| 0.02 | 3.29 | 6000 | 0.1799 | 8.1537 | 5.0354 |
|
| 62 |
+
| 0.019 | 3.84 | 7000 | 0.1801 | 8.125 | 5.0827 |
|
| 63 |
+
| 0.0067 | 4.39 | 8000 | 0.2003 | 7.8412 | 4.8133 |
|
| 64 |
+
| 0.006 | 4.94 | 9000 | 0.2071 | 7.5811 | 4.7023 |
|
| 65 |
+
| 0.0022 | 5.49 | 10000 | 0.2284 | 7.6453 | 4.7187 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
### Framework versions
|
| 69 |
+
|
| 70 |
+
- Transformers 4.26.0.dev0
|
| 71 |
+
- Pytorch 1.13.0+cu117
|
| 72 |
+
- Datasets 2.7.1.dev0
|
| 73 |
+
- Tokenizers 0.13.2
|