whisperkit-coreml

WhisperKit CoreML models for VocaMac

CoreML conversions of Whisper checkpoints that are not published in argmaxinc/whisperkit-coreml, for use with VocaMac.

Each subdirectory is one WhisperKit variant: MelSpectrogram.mlmodelc, AudioEncoder.mlmodelc, TextDecoder.mlmodelc, plus the tokenizer the checkpoint shipped with.

whisper-medium-hindi-hinglish

Converted from shujaAK/whisper-medium-hindi-hinglish-asr-fine-tuned (Apache-2.0, a fine-tune of openai/whisper-medium for Hindi and Hinglish). All credit for the weights goes to the original author; this repository only republishes them in the format WhisperKit loads.

Converted with whisperkittools at fp16, no quantization. The source checkpoint's tokenizer_config.json stores extra_special_tokens as a list, which current transformers rejects; the key is dropped here since those tokens are already in tokenizer.json.

Choosing a language

The fine-tune expects Hindi or Hinglish input and is sensitive to the language you force on it. On a Hinglish sentence ("Kal ka meeting postpone ho gaya hai, so please update the calendar"):

Use Hindi for Devanagari output, auto-detect for English output. Forcing English can return nothing at all. Plain English speech transcribes correctly under any of the three.