Commit
•
ae6bbae
1
Parent(s):
60dae28
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: whisper-large-v2-mn-13
|
| 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 |
+
# whisper-large-v2-mn-13
|
| 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: 0.1689
|
| 20 |
+
- Wer: 20.0240
|
| 21 |
+
- Cer: 6.6010
|
| 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: 4
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 500
|
| 47 |
+
- training_steps: 25000
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:-------:|:---------------:|:-------:|
|
| 54 |
+
| 0.3921 | 0.09 | 1000 | 15.7845 | 0.4101 | 46.9030 |
|
| 55 |
+
| 0.3115 | 0.17 | 2000 | 14.2911 | 0.3353 | 41.8451 |
|
| 56 |
+
| 0.2659 | 0.26 | 3000 | 11.8131 | 0.2800 | 34.6406 |
|
| 57 |
+
| 0.2477 | 0.35 | 4000 | 10.6659 | 0.2578 | 32.0024 |
|
| 58 |
+
| 0.2274 | 0.43 | 5000 | 10.0460 | 0.2463 | 30.3419 |
|
| 59 |
+
| 0.2059 | 0.52 | 6000 | 9.9264 | 0.2305 | 28.5558 |
|
| 60 |
+
| 0.2092 | 0.61 | 7000 | 9.4277 | 0.2196 | 27.8785 |
|
| 61 |
+
| 0.1956 | 0.69 | 8000 | 9.2745 | 0.2093 | 26.8353 |
|
| 62 |
+
| 0.195 | 0.78 | 9000 | 8.9485 | 0.2042 | 26.6168 |
|
| 63 |
+
| 0.195 | 0.87 | 10000 | 8.5324 | 0.2001 | 25.6718 |
|
| 64 |
+
| 0.1795 | 0.95 | 11000 | 8.1786 | 0.1936 | 24.1698 |
|
| 65 |
+
| 0.1575 | 1.04 | 12000 | 7.8653 | 0.1915 | 23.8912 |
|
| 66 |
+
| 0.1358 | 1.13 | 13000 | 7.6749 | 0.1918 | 23.3778 |
|
| 67 |
+
| 0.1509 | 1.21 | 14000 | 7.7221 | 0.1852 | 23.1811 |
|
| 68 |
+
| 0.1474 | 1.3 | 15000 | 7.3246 | 0.1764 | 22.4984 |
|
| 69 |
+
| 0.1461 | 1.39 | 16000 | 7.3187 | 0.1793 | 22.4110 |
|
| 70 |
+
| 0.134 | 1.47 | 17000 | 7.1123 | 0.1737 | 21.9412 |
|
| 71 |
+
| 0.1289 | 1.56 | 18000 | 7.4593 | 0.1727 | 22.0614 |
|
| 72 |
+
| 0.1287 | 1.65 | 19000 | 7.0230 | 0.1701 | 21.4223 |
|
| 73 |
+
| 0.1196 | 1.73 | 20000 | 6.9447 | 0.1666 | 21.2475 |
|
| 74 |
+
| 0.1275 | 1.82 | 21000 | 6.7956 | 0.1653 | 20.8106 |
|
| 75 |
+
| 0.1329 | 1.91 | 22000 | 6.7729 | 0.1622 | 20.3354 |
|
| 76 |
+
| 0.1294 | 1.99 | 23000 | 6.6448 | 0.1606 | 20.2207 |
|
| 77 |
+
| 0.1043 | 2.08 | 24000 | 6.6010 | 0.1689 | 20.0240 |
|
| 78 |
+
| 0.079 | 2.17 | 25000 | 6.6246 | 0.1687 | 20.1005 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.26.0.dev0
|
| 84 |
+
- Pytorch 1.13.1+cu117
|
| 85 |
+
- Datasets 2.8.1.dev0
|
| 86 |
+
- Tokenizers 0.13.2
|