metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- common_voice_11_0
metrics:
- wer
model-index:
- name: whisper-small-hi
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_11_0
type: common_voice_11_0
config: hi
split: test
args: hi
metrics:
- name: Wer
type: wer
value: 32.51079319393888
whisper-small-hi
This model is a fine-tuned version of openai/whisper-small on the common_voice_11_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4405
- Wer: 32.5108
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|
| 0.092 | 2.4450 | 1000 | 0.2986 | 35.0038 |
| 0.0215 | 4.8900 | 2000 | 0.3584 | 33.7171 |
| 0.0012 | 7.3350 | 3000 | 0.4187 | 32.4007 |
| 0.0005 | 9.7800 | 4000 | 0.4405 | 32.5108 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.4.0+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3