Lingalingeswaran/whisper-small-sinhala_v3

Whisper Small sinhala v3 - Lingalingeswaran

This model is a fine-tuned version of openai/whisper-small on the Lingalingeswaran/asr-sinhala-dataset_json_v1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2086
• Wer: 46.4577

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1852	1.7606	1000	0.1875	50.9772
0.0602	3.5211	2000	0.1886	47.5774
0.0238	5.2817	3000	0.2086	46.4577

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0

Example Usage

Here is an example of how to use the model for Sinhala speech recognition with Gradio:

import gradio as gr
from transformers import pipeline

# Initialize the pipeline with the specified model
pipe = pipeline(model="Lingalingeswaran/whisper-small-sinhala_v3")

def transcribe(audio):
    # Transcribe the audio file to text
    text = pipe(audio)["text"]
    return text

# Create the Gradio interface

iface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources=["microphone", "upload"], type="filepath"),
    outputs="text",
    title="Whisper Small Sinhala",
    description="Realtime demo for Sinhala speech recognition using a fine-tuned Whisper small model.",
)

# Launch the interface
if __name__ == "__main__":
    iface.launch()