YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
SoundSense AI - IndicWhisper LoRA Adapter
This is a LoRA fine-tuning adapter for SoundSense AI.
Base model / source:
- openai/whisper-large-v3, https://huggingface.co/openai/whisper-large-v3
Training data:
- MUCS 2021: https://navana-tech.github.io/MUCS2021/
- Kathbath: https://www.openslr.org/103
Use:
- Part of SoundSense AI hackathon submission (Stage 6: Hinglish ASR).
- LoRA rank-8 adapter attached to Whisper-large-v3 for transcribing code-mixed Hindi-English (Hinglish) speech.
Limitations:
- Built for prototype/demo use.
- ASR currently shows transcription errors on wake-word phrases (e.g. "hey jarvis" mistranscribed as "Jandesh"/"Heijarwitz" in pipeline testing).
- Performance should be verified on the target environment before deployment.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support