update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- sacrebleu
|
| 7 |
+
- wer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: la-whisper-small-covost2
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# la-whisper-small-covost2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.5845
|
| 21 |
+
- Sacrebleu: 2090.6716
|
| 22 |
+
- Wer: 73.0006
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-05
|
| 42 |
+
- train_batch_size: 2
|
| 43 |
+
- eval_batch_size: 2
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 16
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 100
|
| 50 |
+
- training_steps: 2000
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu | Wer |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:--------:|
|
| 57 |
+
| 2.6943 | 0.11 | 50 | 2.1667 | 118.2640 | 686.6897 |
|
| 58 |
+
| 1.5505 | 0.23 | 100 | 1.6016 | 259.9307 | 165.6116 |
|
| 59 |
+
| 1.4093 | 0.34 | 150 | 1.5858 | 496.7335 | 197.0106 |
|
| 60 |
+
| 1.3209 | 0.45 | 200 | 1.5648 | 724.2491 | 121.8795 |
|
| 61 |
+
| 1.2941 | 0.56 | 250 | 1.5596 | 820.1241 | 161.7159 |
|
| 62 |
+
| 1.2078 | 0.68 | 300 | 1.5074 | 1022.0043 | 140.3875 |
|
| 63 |
+
| 1.1532 | 0.79 | 350 | 1.4972 | 174.8350 | 610.3716 |
|
| 64 |
+
| 1.0167 | 0.9 | 400 | 1.4551 | 1904.0921 | 82.7635 |
|
| 65 |
+
| 0.8842 | 1.01 | 450 | 1.4296 | 1883.6113 | 81.3906 |
|
| 66 |
+
| 0.5619 | 1.13 | 500 | 1.4333 | 1817.9440 | 84.9312 |
|
| 67 |
+
| 0.5523 | 1.24 | 550 | 1.4237 | 1517.1744 | 104.0918 |
|
| 68 |
+
| 0.4881 | 1.35 | 600 | 1.4413 | 1650.1807 | 97.2067 |
|
| 69 |
+
| 0.471 | 1.46 | 650 | 1.3961 | 1885.0014 | 82.2664 |
|
| 70 |
+
| 0.4412 | 1.58 | 700 | 1.3986 | 2145.9786 | 72.0469 |
|
| 71 |
+
| 0.4625 | 1.69 | 750 | 1.3885 | 1837.7812 | 87.4472 |
|
| 72 |
+
| 0.4195 | 1.8 | 800 | 1.4095 | 1909.2655 | 78.6920 |
|
| 73 |
+
| 0.4532 | 1.91 | 850 | 1.3891 | 1925.2238 | 82.0162 |
|
| 74 |
+
| 0.3201 | 2.03 | 900 | 1.4415 | 1919.2020 | 80.4437 |
|
| 75 |
+
| 0.1955 | 2.14 | 950 | 1.4410 | 1540.5046 | 101.0145 |
|
| 76 |
+
| 0.2111 | 2.25 | 1000 | 1.4345 | 1735.9648 | 90.9269 |
|
| 77 |
+
| 0.1981 | 2.36 | 1050 | 1.4597 | 1730.3250 | 91.5356 |
|
| 78 |
+
| 0.2052 | 2.48 | 1100 | 1.4439 | 2143.3630 | 72.4933 |
|
| 79 |
+
| 0.1886 | 2.59 | 1150 | 1.4702 | 1965.5005 | 77.7519 |
|
| 80 |
+
| 0.1918 | 2.7 | 1200 | 1.4518 | 2057.4517 | 75.4929 |
|
| 81 |
+
| 0.1755 | 2.81 | 1250 | 1.4788 | 1954.2237 | 78.2997 |
|
| 82 |
+
| 0.1769 | 2.93 | 1300 | 1.4588 | 1774.1464 | 91.9279 |
|
| 83 |
+
| 0.1104 | 3.04 | 1350 | 1.5281 | 1838.1999 | 84.7317 |
|
| 84 |
+
| 0.0718 | 3.15 | 1400 | 1.5133 | 2058.0955 | 76.0306 |
|
| 85 |
+
| 0.0855 | 3.26 | 1450 | 1.5271 | 1720.1072 | 89.1346 |
|
| 86 |
+
| 0.0717 | 3.38 | 1500 | 1.5289 | 2007.5163 | 75.9291 |
|
| 87 |
+
| 0.0707 | 3.49 | 1550 | 1.5366 | 2149.6478 | 71.9523 |
|
| 88 |
+
| 0.0704 | 3.6 | 1600 | 1.5355 | 2179.5147 | 69.8759 |
|
| 89 |
+
| 0.0676 | 3.71 | 1650 | 1.5393 | 2086.2197 | 73.2474 |
|
| 90 |
+
| 0.0748 | 3.83 | 1700 | 1.5398 | 1879.1610 | 80.7277 |
|
| 91 |
+
| 0.0695 | 3.94 | 1750 | 1.5351 | 2001.8476 | 78.8306 |
|
| 92 |
+
| 0.033 | 4.05 | 1800 | 1.5807 | 1892.0435 | 82.2630 |
|
| 93 |
+
| 0.0317 | 4.16 | 1850 | 1.5843 | 1967.1172 | 78.7765 |
|
| 94 |
+
| 0.0302 | 4.28 | 1900 | 1.5848 | 1969.6753 | 79.1248 |
|
| 95 |
+
| 0.0337 | 4.39 | 1950 | 1.5808 | 2062.9546 | 74.1537 |
|
| 96 |
+
| 0.0306 | 4.5 | 2000 | 1.5845 | 2090.6716 | 73.0006 |
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
### Framework versions
|
| 100 |
+
|
| 101 |
+
- Transformers 4.28.0.dev0
|
| 102 |
+
- Pytorch 2.0.0
|
| 103 |
+
- Datasets 2.10.1
|
| 104 |
+
- Tokenizers 0.13.2
|