metadata
library_name: transformers
language:
- hi
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: WhisperSmallHindiFineTuned
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: hi
split: test
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 36.74341826800982
WhisperSmallHindiFineTuned
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: 0.1759
- Wer: 36.7434
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 OptimizerNames.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: 100
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2325 | 0.2445 | 100 | 0.2508 | 48.2265 |
| 0.1662 | 0.4890 | 200 | 0.2073 | 42.0681 |
| 0.1415 | 0.7335 | 300 | 0.1884 | 38.7878 |
| 0.1316 | 0.9780 | 400 | 0.1773 | 37.4249 |
| 0.0883 | 1.2225 | 500 | 0.1759 | 36.7434 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0