BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language
Provides the first public ASR resources for the endangered Balti language, enabling further research and applications.
The authors created a 16.8-hour Balti speech corpus and fine-tuned Whisper-small, reducing WER from 182.18% (zero-shot) to 30.07% on a held-out set.
We present BaltiVoice, a 16.8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language spoken in Gilgit-Baltistan, Pakistan, with no prior publicly available ASR resources. The corpus contains 10,060 validated utterances in native Nastaliq script, derived from Mozilla Common Voice recordings. We fine-tune OpenAI Whisper-small on this corpus and report a Word Error Rate (WER) of 30.07% on a held-out validation set of 538 utterances, down from a measured zero-shot baseline of 182.18% for Whisper-small on Balti. The dataset, fine-tuned model, and a live transcription demo are publicly available on HuggingFace.