|
--- |
|
base_model: openai/whisper-large-v3 |
|
datasets: |
|
- mozilla-foundation/common_voice_11_0 |
|
language: |
|
- th |
|
library_name: peft |
|
license: apache-2.0 |
|
metrics: |
|
- wer |
|
- ter |
|
- chrf |
|
- cer |
|
- bleu |
|
- suber |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Whisper Large V3 Thai Lora - Magi Boss |
|
results: |
|
- task: |
|
type: automatic-speech-recognition |
|
name: Automatic Speech Recognition |
|
dataset: |
|
name: Common Voice 11.0 |
|
type: mozilla-foundation/common_voice_11_0 |
|
config: th |
|
split: None |
|
args: 'config: th, split: validation' |
|
metrics: |
|
- type: wer |
|
value: 0.8101 |
|
name: Wer |
|
- name: Ter |
|
type: ter |
|
value: 81.0089 |
|
- name: ChrF |
|
type: chrf |
|
value: 87.4811 |
|
- name: CER |
|
type: cer |
|
value: 0.1041 |
|
- type: bleu |
|
value: 8.7391 |
|
name: Bleu |
|
- name: SubER |
|
type: suber |
|
value: 0.8189 |
|
pipeline_tag: automatic-speech-recognition |
|
--- |
|
|
|
<!-- 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 Large V3 Thai Lora - Magi Boss |
|
|
|
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co./openai/whisper-large-v3) on the Common Voice 11.0 dataset (Training Set 20000 row, Validation Set 500 row). |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1894 |
|
- WER: 0.8101 |
|
- TER: 81.0089 |
|
- ChrF: 87.4811 |
|
- CER: 0.1041 |
|
- BLEU: 8.7391 |
|
- SubER: 0.8189 |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 1e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 25 |
|
- num_epochs: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Ter | Chrf | Cer | Bleu | SubER | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:-------:|:------:|:------:|:---------:| |
|
| 0.3053 | 0.32 | 50 | 0.2052 | 0.8457 | 84.5697 | 86.6971 | 0.1115 | 7.8703 | 0.8640 | |
|
| 0.3752 | 0.64 | 100 | 0.1937 | 0.8323 | 83.2344 | 86.9801 | 0.1087 | 8.1510 | 0.8469 | |
|
| 0.2794 | 0.96 | 150 | 0.1894 | 0.8101 | 81.0089 | 87.4811 | 0.1041 | 8.7391 | 0.8189 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.1.dev0 |
|
- Transformers 4.45.0.dev0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |