mlx-community/Ming-3.0-asr-tiny-bf16

Ming-3.0 ASR Tiny for MLX

Converted from inclusionAI/Ming-3.0-asr-tiny.

English and Chinese transcription. Input audio is resampled to 16 kHz. The audio encoder and MoE routers retain floating-point precision. Speculative MTP decoding and timestamps are not implemented.

from mlx_audio.stt import load
model = load('mlx-community/Ming-3.0-asr-tiny-bf16', strict=True)
result = model.generate("speech.wav")
print(result.text)

Offline inference on Apple Silicon using native MLX code. The tokenizer is loaded without executing remote code.

Source checkpoint revision: b610298956f4d190fa517d396d7e0337a6bf039f.

This export includes all weights and tokenizers needed for its supported tasks. No separate model downloads or ONNX packages are required. Use an MLX Audio version with Ming Tiny support.

The example repository name above may be replaced with the local export directory or your uploaded repository ID.

Validation: strictly reloaded from a relocated directory with an empty Hugging Face cache, network access blocked and ONNX packages absent. See validation.json for the tested tasks and weight inventory. SHA256SUMS covers all package files.