---
language:
- ru
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
model-index:
- name: Whisper Small Ru - BMSTU
  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 Ru - BMSTU

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1876
- Cer: 3.9623

## 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: 500
- training_steps: 4000

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.1707        | 0.4924 | 1000 | 0.2238          | 4.8641 |
| 0.1641        | 0.9847 | 2000 | 0.1984          | 4.1821 |
| 0.0696        | 1.4771 | 3000 | 0.1921          | 4.1234 |
| 0.0712        | 1.9695 | 4000 | 0.1876          | 3.9623 |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.0.1+cu118
- Datasets 2.19.1
- Tokenizers 0.19.1