metadata
library_name: transformers
language:
- fr
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- generated_from_trainer
datasets:
- ras0k/whisper-rap-queb-v5
metrics:
- wer
model-index:
- name: Whisper Quebec Rap - ras0k
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Genius-Quebec-Rap-Top-300
type: ras0k/whisper-rap-queb-v5
config: default
split: None
args: 'config: fr-FR, split: train'
metrics:
- name: Wer
type: wer
value: 32.06981297121673
Whisper Quebec Rap - ras0k
This model is a fine-tuned version of openai/whisper-large-v3 on the Genius-Quebec-Rap-Top-300 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9359
- Wer: 32.0698
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
Github: https://github.com/ras0k/whisper-rap-queb
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 125
- training_steps: 1250
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0 | 0 | 0.8411 | 61.5404 |
| 0.0196 | 13.1579 | 250 | 0.7737 | 32.6363 |
| 0.0033 | 26.3158 | 500 | 0.9160 | 32.2323 |
| 0.0029 | 39.4737 | 750 | 0.9310 | 32.2281 |
| 0.0028 | 52.6316 | 1000 | 0.9361 | 32.2198 |
| 0.0028 | 65.7895 | 1250 | 0.9359 | 32.0698 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.6.1
- Tokenizers 0.22.2