metadata
language:
- hi
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
base_model: openai/whisper-small
model-index:
- name: Whisper Small Hi - Chanpreet Singh
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
args: 'Config: hi'
metrics:
- type: wer
value: 26.011343435198505
name: Wer
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: 0.4519
- Wer: 26.0113
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.1011 | 2.44 | 1000 | 0.3075 | 34.6313 |
| 0.0264 | 4.89 | 2000 | 0.3558 | 33.1288 |
| 0.0025 | 7.33 | 3000 | 0.4214 | 30.5912 |
| 0.0006 | 9.78 | 4000 | 0.4519 | 28.0113 |
| 0.0002 | 12.22 | 5000 | 0.4679 | 26.0960 |