metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_11_0
metrics:
- wer
model-index:
- name: openai/whisper-medium
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_11_0
type: common_voice_11_0
config: id
split: test
args: id
metrics:
- name: Wer
type: wer
value: 8.4616803467675
openai/whisper-medium
This model is a fine-tuned version of openai/whisper-medium on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2935
- Wer: 8.4617
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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0172 | 4.04 | 1000 | 0.2146 | 8.9874 |
| 0.002 | 9.04 | 2000 | 0.2705 | 8.5770 |
| 0.0005 | 14.03 | 3000 | 0.2744 | 8.6692 |
| 0.0003 | 19.03 | 4000 | 0.2890 | 8.5262 |
| 0.0002 | 24.03 | 5000 | 0.2935 | 8.4617 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2