Update moss-transcribe-diarize model card with measured RTF/RAM

196b6d4 verified 10 days ago

5.53 kB

	---
	license: apache-2.0
	base_model: OpenMOSS-Team/MOSS-Transcribe-Diarize
	pipeline_tag: automatic-speech-recognition
	library_name: openasr
	tags:
	- automatic-speech-recognition
	- speech-to-text
	- openasr
	- oasr
	- moss-transcribe-diarize
	---

	<div align="center">

	# MOSS-Transcribe-Diarize · OpenASR

	Joint transcription and speaker diarization in a single 0.9B-parameter model — know who said what, and when

	[![License](https://img.shields.io/badge/license-Apache--2.0-2563eb.svg)](https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize/blob/main/LICENSE)
	[![Format](https://img.shields.io/badge/format-.oasr-7c3aed.svg)](https://github.com/QuintinShaw/openasr)
	[![Runtime](https://img.shields.io/badge/runtime-OpenASR-111827.svg)](https://openasr.org)
	[![Base model](https://img.shields.io/badge/base-MOSS--Transcribe--Diarize-f59e0b.svg)](https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize)

	Native speech-to-text in the [OpenASR](https://github.com/QuintinShaw/openasr) runtime —
	engineered for peak performance on CPU & GPU, no Python at inference time.

	</div>

	---

	## ✨ Highlights

	- 🎯 Transcription + speaker identification in one pass — a single inference run produces both the transcript and per-speaker timestamps, no separate pipeline needed
	- 📊 Verified accuracy: 2.52% CER (Chinese), 2.23% WER (English) — benchmarked by OpenASR on frozen evaluation datasets, not upstream-reported numbers
	- 🌐 Chinese and English first, 15+ additional languages — optimized for Mandarin and English with broad multilingual coverage built in
	- 📦 Three quantization tiers: fp16 / q8_0 / q4_k — delivered in OpenASR's native .oasr format for CPU inference, choose the precision-to-size tradeoff that fits your hardware
	- 🦀 Native in OpenASR — `.oasr` packs run with no Python at inference, engineered for peak performance on CPU & GPU

	## 🚀 Quickstart

	```bash
	# 1. Install the OpenASR CLI · https://openasr.org
	# 2. Pull a build (pick a quant — see the table below)
	openasr pull moss-transcribe-diarize:q8

	# 3. Transcribe
	openasr transcribe audio.wav --model moss-transcribe-diarize
	```

	All builds for this model:

	```bash
	openasr pull moss-transcribe-diarize:fp16
	openasr pull moss-transcribe-diarize:q8
	openasr pull moss-transcribe-diarize:q4
	```

	## 📦 Available builds

	\| Quant \| File (`.oasr`) \| Size \| RAM peak \| RTF · M1 CPU \| RTF · M1 GPU \| JFK ΔWER vs fp16 \|
	\|:------\|:---------------\|-----:\|---------:\|-------------:\|-------------:\|-----------------:\|
	\| fp16 \| `moss-transcribe-diarize-fp16.oasr` \| 1.82 GB \| 4.66 GB \| 0.56× \| 0.36× \| 0.0% \|
	\| q8_0 \| `moss-transcribe-diarize-q8_0.oasr` \| 1.12 GB \| 3.49 GB \| 0.50× \| 0.32× \| 0.0% \|
	\| q4_k \| `moss-transcribe-diarize-q4_k.oasr` \| 902 MB \| 2.99 GB \| 0.47× \| 0.30× \| 0.0% \|

	<sub>RTF = real-time factor on the fixed 11s JFK clip (lower is faster); RAM peak measured per pack
	in an isolated subprocess. JFK ΔWER compares each quantized build's JFK transcript to this model's
	fp16 JFK transcript, so it measures quantization drift rather than absolute recognition accuracy.
	q8_0 is the recommended default — near-reference quality at a fraction of the
	footprint.</sub>

	## 🧠 About MOSS-Transcribe-Diarize

	MOSS-Transcribe-Diarize is a 0.9B-parameter joint speech-recognition and speaker-diarization
	model from the OpenMOSS team. Its architecture pairs a Whisper-Medium-scale audio encoder with a
	lightweight MLP/LayerNorm adapter feeding into a Qwen3-0.6B-scale decoder, enabling the model to
	transcribe speech and attribute each segment to its speaker with start/end timestamps in a single
	forward pass. Language coverage centers on Chinese and English, with support for 15 additional
	languages. OpenASR distributes this model in three quantization tiers -- fp16, q8_0, and q4_k --
	packaged in the native `.oasr` runtime format for CPU-based local inference.

	## ⚙️ How these packs were made

	Converted from [OpenMOSS-Team/MOSS-Transcribe-Diarize](https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize) with the OpenASR importer:

	```bash
	openasr model-pack import moss <src> <out>.oasr \
	--package-id moss-transcribe-diarize --quantization {fp16,q8-0,q4-k}
	```

	The `.oasr` container is GGUF-backed; packs use zero-copy mmap weight binding and graph
	buffer reuse to keep peak memory low.

	## ⚖️ License

	These packs inherit the upstream model's license: Apache-2.0
	([source](https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize/blob/main/LICENSE)). OpenASR packaging retains the upstream copyright and
	NOTICE; the only modifications are format conversion and quantization.

	## 🙏 Acknowledgements

	This pack is a redistribution of MOSS-Transcribe-Diarize, created and released by
	OpenMOSS-Team
	([OpenMOSS-Team/MOSS-Transcribe-Diarize](https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize))
	under the [Apache License 2.0](https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize/blob/main/LICENSE).
	OpenASR performs format conversion, quantization, runtime validation, and local-inference
	adaptation only; all model weights and training are the work of the original authors. Thank you
	to the OpenMOSS team for releasing their work openly.

	## 🔗 Links

	- 🦀 OpenASR — <https://github.com/QuintinShaw/openasr>
	- 🌐 Website — <https://openasr.org>
	- 🤗 Upstream model — [OpenMOSS-Team/MOSS-Transcribe-Diarize](https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize)