convez.ai
MCP ServerIntegração & APIsIntermediário
modelscope

FunASR – Reconhecimento de Fala Industrial

modelscope/FunASR

ASR industrial 170x mais rápido que Whisper com diarização automática

Ver no GitHub
ExcelentePluginScore · de 0 a 100

Toolkit de reconhecimento de fala de nível industrial com suporte a 50+ idiomas, diarização de alto-falantes e detecção de emoções. 170x mais rápido que Whisper, oferece API compatível com OpenAI e streaming em tempo real para transcrição estruturada com timestamps e identificação de falantes.

Instalação

$npx convez-ai modelscope/FunASR

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
21 mil
Forks
2,1 mil
Acompanhando
113
Saúde
87%
Último commit
há 2 dias
Versão
v1.4.27
Issues abertas
66
Contribuidores
179

Casos de uso

  • Transcrição de reuniões com identificação de falantes
  • Processamento de áudio em streaming para aplicações em tempo real
  • Análise de conteúdo de vídeo e podcasts com emoção e speaker labels
  • Substituição drop-in de Whisper em pipelines existentes

Veredito

Solução robusta e performática para ASR em produção. Destaca-se pela velocidade, multilíngue nativo e features avançadas (diarização, emoção) em um único modelo. Ideal para quem precisa migrar de Whisper ou construir pipelines de áudio complexos.

README

A tradução para o português deste README ainda está na fila.

(简体中文|English|日本語|한국어)


Quick Start

Open In Colab

No local setup? Open the Colab quickstart to transcribe a public sample or upload your own audio in a browser.

pip install torch torchaudio
pip install funasr
from funasr import AutoModel

model = AutoModel(model="iic/SenseVoiceSmall", vad_model="fsmn-vad", spk_model="cam++", device="cuda")
result = model.generate(input="meeting.wav")

Output — structured text with speaker labels, timestamps, and punctuation:

[00:00.4 → 00:03.8] Speaker 0: Let's discuss the Q3 plan.
[00:04.2 → 00:07.1] Speaker 1: Sounds good. I have three points.
[00:07.5 → 00:12.3] Speaker 0: Go ahead. We have 30 minutes.

That's it. One model, one call — VAD segmentation, speech recognition, punctuation, speaker diarization all happen automatically.

LLM-powered ASR: Fun-ASR-Nano

For highest accuracy across 31 languages (including Chinese dialects), use Fun-ASR-Nano — an LLM-based ASR combining SenseVoice encoder with Qwen3-0.6B decoder:

from funasr import AutoModel

model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", vad_model="fsmn-vad", device="cuda")
result = model.generate(input="meeting.wav")

With vLLM acceleration (16x faster, batch processing):

from funasr.auto.auto_model_vllm import AutoModelVLLM

model = AutoModelVLLM(model="FunAudioLLM/Fun-ASR-Nano-2512", tensor_parallel_size=1)
results = model.generate(["audio1.wav", "audio2.wav"], language="auto")

Deploy as API server: funasr-server --device cuda → OpenAI-compatible endpoint at localhost:8000

Use with AI agents: MCP Server for Claude/Cursor · OpenAI API for LangChain/Dify/AutoGen

Why FunASR?

FunASRWhisperCloud APIs
Speed170x realtime13x realtime~1x realtime
Speaker ID✅ Built-in❌ Needs pyannote✅ Extra cost
Emotion✅ Happy/Sad/Angry❌❌
Languages50+57Varies
Streaming✅ WebSocket❌✅
vLLM Acceleration✅ 2-3x faster❌N/A
Self-hosted✅ MIT license✅ MIT license❌ Cloud only
CostFreeFree$0.006/min+
CPU viable✅ 17x realtime❌ Too slowN/A

Trying FunASR for the first time? Use the Colab quickstart before setting up a local environment. Choosing a first model? Start with the model selection guide. Planning a switch from Whisper or a cloud ASR provider? Use the migration guide and benchmark example to test representative audio, map features, and roll out safely.


Benchmark

184 long-form audio files (192 min). Full report →

ModelGPU SpeedCPU Speedvs Whisper-large-v3
SenseVoice-Small170x realtime17x realtime🚀 13x faster
Paraformer-Large120x realtime15x realtime🚀 9x faster
Whisper-large-v3-turbo46x realtime❌3.4x faster
Fun-ASR-Nano17x realtime3.6x realtime1.3x faster
Whisper-large-v313x realtime❌baseline

Key takeaway: FunASR models run on CPU faster than Whisper runs on GPU.


What's new

  • 2026/05/24: vLLM Inference Engine — 2-3x faster LLM decoding for Fun-ASR-Nano. Streaming WebSocket service with VAD + Speaker Diarization. Guide →
  • 2026/05/24: Dynamic VAD — adaptive silence threshold (default on). Short sentences stay intact, long segments get auto-split. Details →
  • 2026/05/24: v1.3.3 — funasr-server CLI, OpenAI-compatible API, MCP Server for AI agents. pip install --upgrade funasr
  • 2026/05/20: Added Qwen3-ASR (0.6B/1.7B) — 52 languages, auto detection. usage
  • 2026/05/20: Added GLM-ASR-Nano (1.5B) — 17 languages, dialect support. usage
  • 2026/05/19: Fun-ASR-Nano and SenseVoice now support speaker diarization.
  • 2025/12/15: Fun-ASR-Nano-2512 — 31 languages, tens of millions of hours training.
  • 2024/10/10: Whisper-large-v3-turbo support added.
  • 2024/07/04: SenseVoice — ASR + emotion + audio events.
  • 2024/01/30: FunASR 1.0 released.

Installation

pip install funasr
git clone https://github.com/modelscope/FunASR.git && cd FunASR
pip install -e ./

Requirements: Python ≥ 3.8. Install PyTorch + torchaudio first (pytorch.org), then pip install funasr.


Model Zoo

ModelTaskLanguagesParamsLinks
Fun-ASR-NanoASR + timestamps31 languages800M⭐ 🤗
SenseVoiceSmallASR + emotion + eventszh/en/ja/ko/yue234M⭐ 🤗
Paraformer-zhASR + timestampszh/en220M⭐ 🤗
Paraformer-zh-streamingStreaming ASRzh/en220M⭐ 🤗
Qwen3-ASRASR, 52 languagesmultilingual1.7Busage
GLM-ASR-NanoASR, 17 languagesmultilingual1.5Busage
Whisper-large-v3ASR + translationmultilingual1550Musage
Whisper-large-v3-turboASR + translationmultilingual809Musage
ct-puncPunctuationzh/en290M⭐ 🤗
fsmn-vadVADzh/en0.4M⭐ 🤗
cam++Speaker diarization—7.2M⭐ 🤗
emotion2vec+largeEmotion recognition—300M⭐ 🤗

Usage

Full examples with parameter docs: Tutorial →

from funasr import AutoModel

# Chinese production (VAD + ASR + punctuation + speaker)
model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc", spk_model="cam++", device="cuda")
result = model.generate(input="meeting.wav", hotword="关键词 20")

# 31 languages with timestamps
model = AutoModel(model="FunAudioLLM/Fun-ASR-Nano-2512", hub="hf", trust_remote_code=True,
                  vad_model="fsmn-vad", vad_kwargs={"max_single_segment_time": 30000}, device="cuda")
result = model.generate(input="audio.wav", batch_size=1)

# Streaming real-time
model = AutoModel(model="paraformer-zh-streaming", device="cuda")
result = model.generate(input="chunk.wav", cache={}, chunk_size=[0, 10, 5])

# Emotion recognition
model = AutoModel(model="emotion2vec_plus_large", device="cuda")
result = model.generate(input="audio.wav", granularity="utterance")

CLI (Agent-Friendly)

# Transcribe audio (simplest)
funasr audio.wav

# JSON output (for AI agents)
funasr audio.wav --output-format json

# SRT subtitles
funasr audio.wav --output-format srt --output-dir ./subs

# Speaker diarization + timestamps
funasr audio.wav --spk --timestamps -f json

# Choose model and language
funasr audio.wav --model paraformer --language zh

# Batch transcribe
funasr *.wav --output-format srt --output-dir ./output

Available models: sensevoice (default), paraformer, paraformer-en, fun-asr-nano


Deploy

# OpenAI-compatible API (recommended)
pip install torch torchaudio
pip install funasr vllm fastapi uvicorn python-multipart
funasr-server --device cuda
# → POST /v1/audio/transcriptions at localhost:8000

Verify it with a public sample:

curl -L https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0764W0121.wav -o sample.wav
curl http://localhost:8000/v1/audio/transcriptions \
  -F file=@sample.wav \
  -F model=sensevoice \
  -F response_format=verbose_json
# Docker streaming service
docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.12

OpenAI API example → · Gradio demo → · Client recipes → · JavaScript/TypeScript recipes → · Kubernetes template → · Workflow recipes → · Postman collection → · OpenAPI spec → · Security guide → · Deployment matrix → · Deployment docs → · Agent integration →


Community

📖 Documentation🐛 Issues
💬 Discussions🤗 HuggingFace
🤝 Contributing📈 20k growth plan

Star History

License

MIT License

Citations

@inproceedings{gao2023funasr,
  author={Zhifu Gao and others},
  title={FunASR: A Fundamental End-to-End Speech Recognition Toolkit},
  booktitle={INTERSPEECH},
  year={2023}
}
Ver o original no GitHub

Bom para

Relacionados