Hugging Face's logo

biodatlab
/
whisper-th-medium-combined

Automatic Speech Recognition
Transformers
Safetensors
Thai
whisper
whisper-event
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
5
whisper-th-medium-combined / README.md
tensorops's picture
tensorops
Update README.md
c98d215
preview code
|
raw
history blame
2.52 kB
metadata
language:
  - th
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Medium Thai Combined V2 - biodatlab
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0 th
          type: mozilla-foundation/common_voice_11_0
          config: th
          split: test
          args: th
        metrics:
          - name: Wer
            type: wer
            value: 8.44

Whisper Medium (Thai): Combined V2

This model is a fine-tuned version of biodatlab/whisper-medium-th-1000iter on the mozilla-foundation/common_voice_11_0 th dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1475
  • WER: 13.03 (without Tokenizer)
  • WER: 8.44 (with Deepcut Tokenizer)

Model description

Use the model with huggingface's transformers as follows:

from transformers import pipeline

MODEL_NAME = "biodatlab/whisper-medium-th-combined-v2"  # 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: 32
  • eval_batch_size: 32
  • 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

Training results

Training Loss Epoch Step Validation Loss Wer
0.0679 2.09 5000 0.1475 13.03

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0
  • Datasets 2.7.1
  • Tokenizers 0.13.2