whisper-small-uzbek / README.md
mirodil's picture
trained on CommonVoice13 50%-100%
f14d76f
---
language:
- uz
license: apache-2.0
base_model: openai/whisper-small
tags:
- automatic-speech-recognition
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper Small Uzbek
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Whisper Small Uzbek
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_13_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5058
- Wer Ortho: 45.0514
- Wer: 34.8505
## 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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
| 0.4898 | 0.27 | 500 | 0.5058 | 45.0514 | 34.8505 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0