sanke/trelis-mlx-hinglish-q4
07
Trelis Whisper Hinglish (Preview) - MLX Q4
This is a 4-bit MLX quantized version of the Trelis/whisper-hinglish-preview model by Trelis Research.
Conversion Details
The original model (a fine-tune of whisper-large-v3 for English/Hindi code-switching) has been unsharded and converted to the MLX format with 4-bit quantization. This reduces the memory footprint from ~3.1 GB down to ~733 MB, allowing it to run extremely fast on Apple Silicon (M-series) Macs while maintaining high accuracy.
Usage with MLX
You can load and run this model using the mlx-whisper package:
import mlx_whisper
text = mlx_whisper.transcribe(
"audio.wav",
path_or_hf_repo="sanke/trelis-mlx-hinglish-q4"
)
print(text["text"])Credits & Links
- Original Model: Trelis/whisper-hinglish-preview
- Original Author: Trelis Research
- Framework: MLX (ml-explore)
