metadata
language:
- th
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Large V3 Th - Chee Li
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 11.0
type: mozilla-foundation/common_voice_11_0
config: th
split: None
args: 'config: th split: test'
metrics:
- name: Wer
type: wer
value: 1243.2612539099687
Whisper Large V3 Th - Chee Li
This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0898
- Wer: 1243.2613
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 |
|---|---|---|---|---|
| 0.1662 | 0.3740 | 1000 | 0.1388 | 865.8439 |
| 0.1298 | 0.7479 | 2000 | 0.1118 | 998.3068 |
| 0.062 | 1.1219 | 3000 | 0.0996 | 1036.6313 |
| 0.0609 | 1.4959 | 4000 | 0.0898 | 1243.2613 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1