MOSS-Transcribe-Diarize-mlx-8bit

MOSS-Transcribe-Diarize 0.9B is an end-to-end audio understanding model for long-form multi-speaker transcription, diarization, timestamps, and acoustic event awareness.

8-bit MLX quantization of OpenMOSS-Team/MOSS-Transcribe-Diarize

Usage

import mlx_audio.stt as stt

model_id = "ziyu12345/MOSS-Transcribe-Diarize-mlx-8bit"
model = stt.load(model_id)
result = model.generate("test_asr.wav", language="English")
print(result.text)
for segment in result.segments:
    print(f"[{segment['start']:.2f}s - {segment['end']:.2f}s] Speaker {segment['speaker_id']}: {segment['text']}")
Downloads last month
49
Safetensors
Model size
0.5B params
Tensor type
BF16
·
U32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ziyu12345/MOSS-Transcribe-Diarize-mlx-8bit

Quantized
(11)
this model