whisper-small-ru / README.md
whitemouse84's picture
End of training
7cd528c verified
---
language:
- ru
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_0
metrics:
- wer
model-index:
- name: Whisper Base Ru
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 16.0
type: mozilla-foundation/common_voice_16_0
config: ru
split: None
args: 'config: ru, split: test'
metrics:
- name: Wer
type: wer
value: 131.35769718547476
---
<!-- 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 Base Ru
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2080
- Wer: 131.3577
## 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
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.2013 | 0.61 | 1000 | 0.2301 | 130.4397 |
| 0.0753 | 1.21 | 2000 | 0.2159 | 131.7603 |
| 0.0902 | 1.82 | 3000 | 0.2046 | 129.7846 |
| 0.0394 | 2.43 | 4000 | 0.2080 | 131.3577 |
### Framework versions
- Transformers 4.37.2
- Pytorch 2.2.2
- Datasets 2.18.0
- Tokenizers 0.15.1