metadata
language:
- uz
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
model-index:
- name: Whisper Small Uz - Makhmud Jumanazarov
results: []
Whisper Small Uz - Makhmud Jumanazarov
This model is a fine-tuned version of openai/whisper on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3416
- Wer: 34.9285
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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 |
|---|---|---|---|---|
| 0.4794 | 0.54 | 1000 | 0.4504 | 42.0722 |
| 0.313 | 1.08 | 2000 | 0.3821 | 38.9392 |
| 0.2948 | 1.62 | 3000 | 0.3468 | 35.4270 |
| 0.249 | 2.16 | 4000 | 0.3416 | 34.9285 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0