metadata
language:
- vi
base_model: openai/whisper-tiny-vi-v1
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Tiny Vi - Anh Phuong
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: vi 500
type: mozilla-foundation/common_voice_11_0
args: 'config: hi, split: test'
metrics:
- name: Wer
type: wer
value: 17.927542787107694
Whisper Tiny Vi - Anh Phuong
This model is a fine-tuned version of openai/whisper-tiny-vi-v1 on the vi 500 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3071
- Wer: 17.9275
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: 4
- 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 |
|---|---|---|---|---|
| 0.4594 | 0.16 | 1000 | 0.4406 | 24.6174 |
| 0.3731 | 0.32 | 2000 | 0.3586 | 20.4809 |
| 0.3199 | 0.48 | 3000 | 0.3223 | 18.8015 |
| 0.3026 | 0.64 | 4000 | 0.3071 | 17.9275 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1