metadata
base_model: openai/whisper-medium
datasets:
- miosipof/asr_en
language:
- en
library_name: peft
license: apache-2.0
metrics:
- wer
tags:
- generated_from_trainer
model-index:
- name: Whisper Medium
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: miosipof/asr_en
type: miosipof/asr_en
config: default
split: train
args: default
metrics:
- type: wer
value: 68.88888888888889
name: Wer
Whisper Medium
This model is a fine-tuned version of openai/whisper-medium on the miosipof/asr_en dataset. It achieves the following results on the evaluation set:
- Loss: 0.3857
- Wer: 68.8889
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 32
- training_steps: 1024
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.6529 | 1.0847 | 32 | 2.0524 | 41.1111 |
| 1.2225 | 2.1695 | 64 | 0.6093 | 52.0635 |
| 0.2888 | 3.2542 | 96 | 0.4636 | 48.5714 |
| 0.1701 | 4.3390 | 128 | 0.4190 | 43.0159 |
| 0.1729 | 5.4237 | 160 | 0.5561 | 61.9048 |
| 0.0846 | 6.5085 | 192 | 0.3515 | 57.3016 |
| 0.0678 | 7.5932 | 224 | 0.3795 | 47.9365 |
| 0.0578 | 8.6780 | 256 | 0.5905 | 56.9841 |
| 0.0457 | 9.7627 | 288 | 0.4444 | 73.0159 |
| 0.0432 | 10.8475 | 320 | 0.5010 | 59.2063 |
| 0.0407 | 11.9322 | 352 | 0.5758 | 63.4921 |
| 0.0341 | 13.0169 | 384 | 0.6487 | 50.3175 |
| 0.0308 | 14.1017 | 416 | 0.4682 | 45.8730 |
| 0.0304 | 15.1864 | 448 | 0.4518 | 65.5556 |
| 0.0241 | 16.2712 | 480 | 0.5138 | 64.2857 |
| 0.029 | 17.3559 | 512 | 0.5460 | 66.5079 |
| 0.0169 | 18.4407 | 544 | 0.6139 | 64.7619 |
| 0.0196 | 19.5254 | 576 | 0.6055 | 54.4444 |
| 0.0148 | 20.6102 | 608 | 0.4502 | 65.7143 |
| 0.0153 | 21.6949 | 640 | 0.4179 | 81.7460 |
| 0.0149 | 22.7797 | 672 | 0.4491 | 108.7302 |
| 0.0188 | 23.8644 | 704 | 0.3885 | 75.3968 |
| 0.0115 | 24.9492 | 736 | 0.4070 | 182.6984 |
| 0.0111 | 26.0339 | 768 | 0.4429 | 128.7302 |
| 0.0124 | 27.1186 | 800 | 0.3827 | 69.2063 |
| 0.0096 | 28.2034 | 832 | 0.4028 | 70.0 |
| 0.0121 | 29.2881 | 864 | 0.3651 | 63.8095 |
| 0.0083 | 30.3729 | 896 | 0.3906 | 66.6667 |
| 0.0085 | 31.4576 | 928 | 0.3861 | 66.8254 |
| 0.0092 | 32.5424 | 960 | 0.3834 | 69.6825 |
| 0.0095 | 33.6271 | 992 | 0.3861 | 68.8889 |
| 0.007 | 34.7119 | 1024 | 0.3857 | 68.8889 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1