Fine-tuned openai/whisper-large-v3-turbo on Monsoon Hindi ASR data using LoRA (r=32, alpha=64). English capabilities preserved with <10% relative degradation across all benchmarks. LoRA's structural separation (frozen base + low-rank adapters) provides a natural safeguard against catastrophic forgetting.
Independent publisher
Hrushi Borhade
annotehrushi
Models in Library1
Datasets in Library0
Models on Hugging Face1
Followers—