Commit
•
7f70a60
1
Parent(s):
3a1d924
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: whisper-medium-mn-4
|
| 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-medium-mn-4
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6015
|
| 20 |
+
- Wer: 33.0293
|
| 21 |
+
- Cer: 10.9236
|
| 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: 32
|
| 42 |
+
- eval_batch_size: 16
|
| 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: 15000
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
|
| 54 |
+
| 0.0362 | 4.26 | 1000 | 0.4204 | 40.2720 | 13.8389 |
|
| 55 |
+
| 0.0087 | 8.51 | 2000 | 0.4712 | 37.4918 | 12.9175 |
|
| 56 |
+
| 0.0044 | 12.77 | 3000 | 0.4893 | 36.3393 | 12.4727 |
|
| 57 |
+
| 0.0033 | 17.02 | 4000 | 0.5159 | 35.8423 | 12.2933 |
|
| 58 |
+
| 0.0017 | 21.28 | 5000 | 0.5183 | 35.2797 | 12.1104 |
|
| 59 |
+
| 0.0016 | 25.53 | 6000 | 0.5422 | 35.4326 | 11.7454 |
|
| 60 |
+
| 0.0011 | 29.79 | 7000 | 0.5361 | 34.5314 | 11.5196 |
|
| 61 |
+
| 0.0004 | 34.04 | 8000 | 0.5406 | 34.0998 | 11.3650 |
|
| 62 |
+
| 0.0006 | 38.3 | 9000 | 0.5540 | 33.8650 | 11.2912 |
|
| 63 |
+
| 0.0002 | 42.55 | 10000 | 0.5748 | 34.0889 | 11.5333 |
|
| 64 |
+
| 0.0003 | 46.81 | 11000 | 0.5771 | 34.5641 | 11.4895 |
|
| 65 |
+
| 0.0 | 51.06 | 12000 | 0.5809 | 33.4335 | 11.2070 |
|
| 66 |
+
| 0.0 | 55.32 | 13000 | 0.5941 | 33.2095 | 11.0009 |
|
| 67 |
+
| 0.0 | 59.57 | 14000 | 0.6015 | 33.0293 | 10.9236 |
|
| 68 |
+
| 0.0 | 63.83 | 15000 | 0.6045 | 33.0347 | 10.9125 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.26.0.dev0
|
| 74 |
+
- Pytorch 1.13.0+cu117
|
| 75 |
+
- Datasets 2.7.1.dev0
|
| 76 |
+
- Tokenizers 0.13.2
|