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-BTCv2
|
| 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-BTCv2
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4025
|
| 20 |
+
- Wer: 7.3302
|
| 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: 3e-06
|
| 40 |
+
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 16
|
| 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: 600
|
| 46 |
+
- training_steps: 800
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 0.7348 | 2.01 | 50 | 0.7378 | 9.3091 |
|
| 54 |
+
| 0.5276 | 4.02 | 100 | 0.5290 | 8.6125 |
|
| 55 |
+
| 0.3585 | 7.0 | 150 | 0.3875 | 6.5315 |
|
| 56 |
+
| 0.2924 | 9.01 | 200 | 0.3548 | 6.6779 |
|
| 57 |
+
| 0.2506 | 11.02 | 250 | 0.3364 | 6.7888 |
|
| 58 |
+
| 0.1946 | 14.01 | 300 | 0.3262 | 7.1482 |
|
| 59 |
+
| 0.1411 | 16.02 | 350 | 0.3329 | 7.2104 |
|
| 60 |
+
| 0.1005 | 19.0 | 400 | 0.3422 | 7.5565 |
|
| 61 |
+
| 0.0535 | 21.01 | 450 | 0.3532 | 7.1793 |
|
| 62 |
+
| 0.0259 | 23.02 | 500 | 0.3456 | 7.5121 |
|
| 63 |
+
| 0.0137 | 26.0 | 550 | 0.3587 | 7.6541 |
|
| 64 |
+
| 0.0078 | 28.02 | 600 | 0.3591 | 7.3524 |
|
| 65 |
+
| 0.0041 | 30.02 | 650 | 0.3672 | 7.3035 |
|
| 66 |
+
| 0.0026 | 33.01 | 700 | 0.3962 | 7.3213 |
|
| 67 |
+
| 0.0022 | 35.02 | 750 | 0.3997 | 7.3524 |
|
| 68 |
+
| 0.0022 | 38.0 | 800 | 0.4025 | 7.3302 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.27.0.dev0
|
| 74 |
+
- Pytorch 1.13.1+cu117
|
| 75 |
+
- Datasets 2.9.1.dev0
|
| 76 |
+
- Tokenizers 0.13.2
|