README.md

metadata

license: apache-2.0
base_model: biodatlab/whisper-th-small-combined
tags:
  - generated_from_trainer
datasets:
  - common_voice_17_0
metrics:
  - wer
model-index:
  - name: Whisper-small-thai
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: common_voice_17_0
          type: common_voice_17_0
          config: th
          split: test
          args: th
        metrics:
          - name: Wer
            type: wer
            value: 55.432891743610334
language:
  - th
pipeline_tag: automatic-speech-recognition

Whisper-small-thai

This model is a fine-tuned version of biodatlab/whisper-th-small-combined on the common_voice_17_0 dataset.

Model description

Use the model with huggingface's transformers as follows:

from transformers import pipeline

MODEL_NAME = "FILM6912/Whisper-small-thai"  # specify the model name
lang = "th"  # change to Thai langauge

device = 0 if torch.cuda.is_available() else "cpu"

pipe = pipeline(
    task="automatic-speech-recognition",
    model=MODEL_NAME,
    chunk_length_s=30,
    device=device,
)
pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(
  language=lang,
  task="transcribe"
)
text = pipe("audio.mp3")["text"] # give audio mp3 and transcribe text

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: 5000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1