update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: whisper-small-toi
|
| 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-small-toi
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 3.1668
|
| 20 |
+
- Wer: 63.5938
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 1e-05
|
| 40 |
+
- train_batch_size: 4
|
| 41 |
+
- eval_batch_size: 4
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 500
|
| 46 |
+
- training_steps: 10000
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
|
| 53 |
+
| 0.568 | 1.47 | 500 | 2.1883 | 72.0402 |
|
| 54 |
+
| 0.2614 | 2.95 | 1000 | 2.1071 | 67.1034 |
|
| 55 |
+
| 0.0811 | 4.42 | 1500 | 2.3456 | 67.5012 |
|
| 56 |
+
| 0.0383 | 5.9 | 2000 | 2.4961 | 67.9691 |
|
| 57 |
+
| 0.021 | 7.37 | 2500 | 2.6259 | 68.8348 |
|
| 58 |
+
| 0.0077 | 8.85 | 3000 | 2.6423 | 66.6823 |
|
| 59 |
+
| 0.0046 | 10.32 | 3500 | 2.8497 | 65.9336 |
|
| 60 |
+
| 0.0005 | 11.8 | 4000 | 2.8305 | 64.6467 |
|
| 61 |
+
| 0.0014 | 13.27 | 4500 | 2.9174 | 66.0739 |
|
| 62 |
+
| 0.0003 | 14.75 | 5000 | 2.9358 | 63.2663 |
|
| 63 |
+
| 0.0002 | 16.22 | 5500 | 2.9820 | 63.8278 |
|
| 64 |
+
| 0.0002 | 17.7 | 6000 | 3.0369 | 64.7403 |
|
| 65 |
+
| 0.0001 | 19.17 | 6500 | 3.0641 | 63.3832 |
|
| 66 |
+
| 0.0005 | 20.65 | 7000 | 3.0512 | 63.1493 |
|
| 67 |
+
| 0.0001 | 22.12 | 7500 | 3.0924 | 63.5002 |
|
| 68 |
+
| 0.0001 | 23.6 | 8000 | 3.1215 | 65.0679 |
|
| 69 |
+
| 0.0001 | 25.07 | 8500 | 3.1336 | 64.6233 |
|
| 70 |
+
| 0.0001 | 26.55 | 9000 | 3.1513 | 63.7108 |
|
| 71 |
+
| 0.0001 | 28.02 | 9500 | 3.1620 | 63.5938 |
|
| 72 |
+
| 0.0001 | 29.5 | 10000 | 3.1668 | 63.5938 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.26.0.dev0
|
| 78 |
+
- Pytorch 1.12.1+cu113
|
| 79 |
+
- Datasets 2.7.1
|
| 80 |
+
- Tokenizers 0.13.2
|