metadata
language:
- uz
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_1
metrics:
- wer
model-index:
- name: Whisper Small Uz - Bahriddin Mo'minov
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 16.1
type: mozilla-foundation/common_voice_16_1
config: uz
split: test
args: 'config: uz, split: test'
metrics:
- name: Wer
type: wer
value: 37.07903050585018
Whisper Small Uz - Bahriddin Mo'minov
This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3759
- Wer: 37.0790
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: 8
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 |
|---|---|---|---|---|
| 0.6057 | 0.26 | 1000 | 0.5283 | 46.5667 |
| 0.436 | 0.53 | 2000 | 0.4354 | 42.1575 |
| 0.4144 | 0.79 | 3000 | 0.3925 | 38.4788 |
| 0.3194 | 1.06 | 4000 | 0.3759 | 37.0790 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2