Whisper Medium Ml

🚀 Whisper Medium Malayalam

This model is a fine - tuned version of [openai/whisper - medium](https://huggingface.co/openai/whisper - medium), designed to enhance automatic speech recognition for Malayalam.

🚀 Quick Start

This model is a fine - tuned version of [openai/whisper - medium](https://huggingface.co/openai/whisper - medium) on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• WER: 38.6207
• CER: 7.3256

Note that Whisper's normalization has major issues for languages like Malayalam, so the above scores are evaluated without using normalization. With normalization (for a fair comparison with other models on this platform), the results are instead:

• WER: 11.49

[This Colab](https://colab.research.google.com/github/sanchit - gandhi/notebooks/blob/main/fine_tune_whisper.ipynb) can be used as a starting point to further finetune the model.

💻 Usage Examples

Basic Usage

from transformers import pipeline, WhisperProcessor

processor = WhisperProcessor.from_pretrained("thennal/whisper-medium-ml")
forced_decoder_ids = processor.get_decoder_prompt_ids(language="ml", task="transcribe")
asr = pipeline(
        "automatic-speech-recognition", model="thennal/whisper-medium-ml", device=0,
    )
transcription = asr(audio, chunk_length_s=30, max_new_tokens=448, return_timestamps=False,  generate_kwargs={
        "forced_decoder_ids": forced_decoder_ids, 
        "do_sample": True,
    })

📚 Documentation

Model Details

Model Index

• Name: Whisper Medium Malayalam - Thennal D K
  • Results:
    • Task:
      • Type: automatic - speech - recognition
      • Name: Automatic Speech Recognition
    • Dataset:
      • Name: Common Voice 11.0
      • Type: mozilla - foundation/common_voice_11_0
      • Config: ml
      • Split: test
      • Args: ml
    • Metrics:
      • Type: wer
      • Value: 11.49
      • Name: WER

Training Procedure

Training Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e - 05
• train_batch_size: 32
• eval_batch_size: 16
• 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: 8000
• mixed_precision_training: Native AMP

Framework Versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2

📄 License

This model is licensed under the Apache - 2.0 license.