metadata
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- common_voice_9_0
metrics:
- wer
model-index:
- name: cv9-special-batch4-small
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_9_0
type: common_voice_9_0
config: id
split: test
args: id
metrics:
- name: Wer
type: wer
value: 12.564987347596043
cv9-special-batch4-small
This model is a fine-tuned version of openai/whisper-small on the common_voice_9_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2427
- Wer: 12.5650
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: 4
- eval_batch_size: 2
- 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: 5000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3372 | 0.48 | 1000 | 0.2893 | 16.1123 |
| 0.2785 | 0.97 | 2000 | 0.2590 | 14.6032 |
| 0.1318 | 1.45 | 3000 | 0.2535 | 13.8532 |
| 0.1384 | 1.94 | 4000 | 0.2333 | 12.4316 |
| 0.0541 | 2.42 | 5000 | 0.2427 | 12.5650 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3