metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: openai/whisper-small.en
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: rishabhjain16/infer_myst
type: rishabhjain16/infer_myst
config: en
split: test
metrics:
- type: wer
value: 13.43
name: WER
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: rishabhjain16/infer_pfs
type: rishabhjain16/infer_pfs
config: en
split: test
metrics:
- type: wer
value: 3.39
name: WER
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: rishabhjain16/infer_cmu_9h
type: rishabhjain16/infer_cmu_9h
config: en
split: test
metrics:
- type: wer
value: 15.54
name: WER
openai/whisper-small.en
This model is a fine-tuned version of openai/whisper-small.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3955
- Wer: 11.3610
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2871 | 0.12 | 500 | 0.3313 | 12.0452 |
| 0.2339 | 1.11 | 1000 | 0.3023 | 12.9337 |
| 0.2437 | 2.1 | 1500 | 0.3038 | 12.7260 |
| 0.0485 | 3.09 | 2000 | 0.3246 | 11.1822 |
| 0.0834 | 4.07 | 2500 | 0.3510 | 11.8941 |
| 0.1024 | 5.06 | 3000 | 0.3645 | 11.6309 |
| 0.0208 | 6.05 | 3500 | 0.4008 | 10.8457 |
| 0.0328 | 7.03 | 4000 | 0.3955 | 11.3610 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2