inclusionAI/Ming-3.0-asr-tiny

Overview

Ming-3.0-asr-tiny supports Chinese, English, and dialect transcription with optional topic, hotword, and dialogue context. This guide covers single-GPU serving, transcription, streaming, Context ASR, and offline inference with vLLM.

Public example audio

Download the three clips from the official inference repository:

MING_AUDIO_BASE=https://raw.githubusercontent.com/inclusionAI/Ming-3.0-asr/6141e8c552815db724d8df0f72c9d865c547a1ea/examples/cases/audio
curl -fL "$MING_AUDIO_BASE/english_common_voice.wav" -o english.wav
curl -fL "$MING_AUDIO_BASE/chinese_common_voice.wav" -o chinese.wav
curl -fL "$MING_AUDIO_BASE/context_same_sentence_pcm16.wav" -o context.wav

The Context clip illustrates correction of 铜球 to 同囚 with a relevant topic and hotwords. These are sample-specific observations, not a general Context ASR accuracy claim. Audio provenance and licenses are documented in the official examples.

For accuracy comparisons, keep batch settings and attention backends consistent; greedy transcription outputs can differ across these configurations.

Transcription API

Use the audio requests below to verify speech recognition. The catalog's generic text-only cURL and benchmark shortcuts do not exercise ASR.

curl http://localhost:8000/v1/audio/transcriptions \
  -F model=inclusionAI/Ming-3.0-asr-tiny \
  -F file=@chinese.wav \
  -F temperature=0 \
  -F max_completion_tokens=256 \
  -F 'vllm_xargs={"no_repeat_ngram_size":10}'

Omit language for automatic recognition, or use language=zh / language=en to seed the known language. These are the supported language-hint codes; dialect transcription does not introduce additional hint codes. The response contains the transcript without the generated language label. response_format=json and response_format=text are supported.

OpenAI Python client

import json
from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
with open("english.wav", "rb") as audio:
    result = client.audio.transcriptions.create(
        model="inclusionAI/Ming-3.0-asr-tiny",
        file=audio,
        temperature=0,
        extra_body={
            "max_completion_tokens": 256,
            "vllm_xargs": json.dumps({"no_repeat_ngram_size": 10}),
        },
    )
print(result.text)

vllm_xargs is JSON-encoded for the multipart request, as in the cURL examples.

Context ASR

curl http://localhost:8000/v1/audio/transcriptions \
  -F model=inclusionAI/Ming-3.0-asr-tiny \
  -F file=@context.wav \
  -F language=zh \
  -F temperature=0 \
  -F max_completion_tokens=256 \
  -F 'prompt=This is an audio about 同囚.' \
  -F 'hotwords=同囚,黄国权,游学修,关楚耀,赵永洪,赵咏瑶,狱警,长镜头,吞玻璃戏,糖化玻璃,真实案例数据.' \
  -F 'vllm_xargs={"no_repeat_ngram_size":10,"context_chunks":true}'

prompt accepts topic or preceding dialogue appended to the official ASR instruction, or the full official instruction followed by context. Context and hotwords must be single-line text without audio placeholders. To reproduce the vendor's full prompt exactly, put its hotword text in prompt and omit the separate hotwords field.

Streaming

curl -N http://localhost:8000/v1/audio/transcriptions \
  -F model=inclusionAI/Ming-3.0-asr-tiny \
  -F file=@english.wav \
  -F language=en \
  -F temperature=0 \
  -F stream=true \
  -F max_completion_tokens=256 \
  -F 'vllm_xargs={"no_repeat_ngram_size":10}'

Streaming sends transcript deltas after the complete audio upload. It is not live microphone input. The English clip produces same way you did without leaking the language prefix into the transcript.

Chunking and repetition control

Audio is downmixed and resampled to 16 kHz using torchaudio. The processor extracts the entire clip's log-mel features before splitting encoder chunks. Chunk settings are request-local and are included in multimodal cache keys.

context_chunks and an explicit audio_chunk_frames are mutually exclusive. Ordinary chunking can handle clips beyond 60 seconds within the shared 8,192-token input/output budget and audio-upload size limit. Internal encoder chunking does not create separate transcription requests.

The no-repeat feature loads a plugin; each request must still set a nonzero no_repeat_ngram_size to enable blocking. Omitted values and 0 leave ordinary sampling in effect. Blocking uses the full prompt/output history, and requires Model Runner V2. Speculative decoding and MTP are unsupported with this plugin.

Offline inference

From the same vLLM source checkout, use the shared audio language model example with its built-in audio assets:

python examples/generate/multimodal/audio_language_offline.py --model-type ming_v3_asr

This uses the shared example's sampling defaults (temperature=0.2, max_tokens=64) and prints raw model output, including the language label. For the downloaded Context clip, use the native prompt builder with greedy decoding and 10-gram blocking:

from vllm import LLM, SamplingParams
from vllm.config.speech_to_text import SpeechToTextParams
from vllm.model_executor.models.ming_v3_asr import (
    MingV3ASRForConditionalGeneration as MingASR,
)
from vllm.multimodal.audio import AudioResampler
from vllm.multimodal.media.audio import load_audio

def main():
    llm = LLM(
        model="inclusionAI/Ming-3.0-asr-tiny",
        trust_remote_code=True,
        dtype="bfloat16",
        max_model_len=8192,
        max_num_seqs=4,
        enforce_eager=True,
        logits_processors=[
            "vllm.model_executor.models.ming_v3_asr_logits_processor:"
            "NoRepeatNGramLogitsProcessor",
        ],
    )
    audio, rate = load_audio("context.wav", sr=None, mono=True)
    audio = AudioResampler(16000).resample(audio, orig_sr=rate)
    params = SpeechToTextParams(
        audio=audio,
        stt_config=MingASR.get_speech_to_text_config(llm.model_config, "transcribe"),
        model_config=llm.model_config,
        language="zh",
        request_prompt="This is an audio about 同囚.",
        hotwords=(
            "同囚,黄国权,游学修,关楚耀,赵永洪,赵咏瑶,狱警,长镜头,"
            "吞玻璃戏,糖化玻璃,真实案例数据."
        ),
        extra_args={"context_chunks": True},
    )
    outputs = llm.generate(
        MingASR.get_generation_prompt(params),
        SamplingParams(
            temperature=0,
            max_tokens=256,
            extra_args={"no_repeat_ngram_size": 10},
        ),
    )
    print(MingASR.post_process_output(outputs[0].outputs[0].text))


if __name__ == "__main__":
    main()

Limitations

The official model card describes transcription text output without word-level timestamps or speaker diarization.

The current vLLM integration does not support translation, segment timestamps, or live audio input. Translation and timestamp requests are rejected. The context_chunks=true policy accepts clips up to 60 seconds; ordinary chunking, including requests with context prompts, can accept longer clips subject to the model context and upload limits. Longer recordings can produce incomplete transcripts; accepting an upload does not guarantee complete transcription.

References

• model card
• Official inference repository
• vLLM speech-to-text API