metadata
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: Whisper Small Vi - Sonkn
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: vi
split: None
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 28.775084987388965
Whisper Small Vi - Sonkn
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: 0.5243
- Wer: 28.7751
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3284 | 0.1149 | 20 | 0.5643 | 29.8388 |
| 0.2493 | 0.2299 | 40 | 0.5457 | 29.1150 |
| 0.2381 | 0.3448 | 60 | 0.5389 | 29.4550 |
| 0.1865 | 0.4598 | 80 | 0.5303 | 28.9615 |
| 0.1918 | 0.5747 | 100 | 0.5243 | 28.7751 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1