Model reference · open weights
paraformer-zh is an open-weight audio or speech model from funasr. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | funasr |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Runs with | funasr |
| Released | 2024-02-01 |
| Popularity | 1k downloads / month |
| Licence | Open weights |
About
This model is part of the FunASR ecosystem — one industrial-grade open-source toolkit for ASR · VAD · punctuation · speaker diarization · emotion / event · LLM-ASR. A Star really helps the project (and keeps you updated):
Non-autoregressive end-to-end speech recognition — 120x realtime on GPU, production-ready for Mandarin Chinese.
Paraformer is a non-autoregressive (NAR) ASR model that generates the entire output in parallel, achieving significant speedups over autoregressive models like Whisper while maintaining competitive accuracy.
from funasr import AutoModel
# Basic recognition
model = AutoModel(model="funasr/paraformer-zh", hub="hf", device="cuda")
result = model.generate(input="audio.wav")
print(result[0]["text"])
from funasr import AutoModel
model = AutoModel(
model="funasr/paraformer-zh",
hub="hf",
vad_model="funasr/fsmn-vad",
punc_model="funasr/ct-punc",
spk_model="funasr/campplus",
device="cuda",
)
result = model.generate(input="meeting.wav")
# Output includes timestamps, punctuation, and speaker labels
for sentence in result[0]["sentence_info"]:
print(f"[Speaker {sentence['spk']}] {sentence['text']}")
| Property | Value |
|---|---|
| Architecture | Paraformer (Non-autoregressive) |
| Parameters | 220M |
| Languages | Chinese, English |
| Sample Rate | 16kHz |
| Training Data | 60,000+ hours |
| Model | Description | Link |
|---|---|---|
| funasr/fsmn-vad | Voice Activity Detection | HF |
| funasr/ct-punc | Punctuation Restoration | HF |
| funasr/campplus | Speaker Verification | HF |
| funasr/paraformer-zh-streaming | Streaming version | HF |
@inproceedings{gao2022paraformer,
title={Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition},
author={Gao, Zhifu and Zhang, Shiliang and McLoughlin, Ian and Yan, Zhijie},
booktitle={INTERSPEECH},
year={2022}
}
From the published model card. Full card on the HuggingFace links in the sidebar.
How it works
Using it via the API
Once AxForge deploys paraformer-zh for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (paraformer-zh below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="paraformer-zh" -F file=@audio.mp3
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.