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-batch12-lr6-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: train
args: id
metrics:
- name: Wer
type: wer
value: 4.711435314310234
cv9-special-batch12-lr6-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: 0.1223
- Wer: 4.7114
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-06
- train_batch_size: 12
- eval_batch_size: 6
- 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 |
---|---|---|---|---|
0.3296 | 2.38 | 1000 | 0.3019 | 13.1474 |
0.2247 | 4.75 | 2000 | 0.2060 | 8.7041 |
0.1526 | 7.13 | 3000 | 0.1562 | 6.2197 |
0.1476 | 9.5 | 4000 | 0.1304 | 5.0354 |
0.1173 | 11.88 | 5000 | 0.1223 | 4.7114 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3