vanshnawander/whisper-small-telugu

This is a fine-tuned version of openai/whisper-small for Telugu automatic speech recognition (ASR).

Model Description

• Base Model: openai/whisper-small
• Language: Telugu (te)
• Task: Automatic Speech Recognition (transcribe)
• Training Data: ai4bharat/Kathbath
• Fine-tuning Framework: Transformers + Custom DALI Pipeline

Training Details

The model was fine-tuned on the Kathbath Telugu dataset with the following configuration:

• Epochs: 3
• Batch Size: 16 (effective ~96 with gradient accumulation)
• Learning Rate: 1e-5
• Mixed Precision: FP16
• Gradient Checkpointing: Enabled

Evaluation Results

Evaluated on the Shrutilipi benchmark - a large-scale ASR dataset for Indian languages.

Usage

Basic Usage

from transformers import WhisperProcessor, WhisperForConditionalGeneration
import librosa

# Load model and processor
processor = WhisperProcessor.from_pretrained("vanshnawander/whisper-small-telugu")
model = WhisperForConditionalGeneration.from_pretrained("vanshnawander/whisper-small-telugu")

# Load audio
audio, sr = librosa.load("audio.wav", sr=16000)

# Transcribe
input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features
generated_ids = model.generate(input_features, language="te", task="transcribe")
transcription = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(transcription)

Using Pipeline

from transformers import pipeline

pipe = pipeline(
    "automatic-speech-recognition",
    model="vanshnawander/whisper-small-telugu",
    chunk_length_s=30,
)

result = pipe("audio.wav", generate_kwargs={"language": "te", "task": "transcribe"})
print(result["text"])

Limitations

• Optimized for Telugu speech; may not perform well on other languages
• Best performance on clear audio with minimal background noise
• May struggle with very fast speech or heavy code-mixing

Citation

If you use this model, please cite:

@misc{vanshnawander_whisper_small_telugu},
  author = {Vansh Nawander},
  title = {vanshnawander/whisper-small-telugu},
  year = {2025},
  publisher = {HuggingFace},
  url = {https://huggingface.co/vanshnawander/whisper-small-telugu}
}

Acknowledgments

• OpenAI Whisper for the base model
• AI4Bharat for the Kathbath and Shrutilipi datasets
• Hugging Face for the transformers library