Pretrained Models on Huggingface
Model License
The FunASR toolkit uses the MIT software license. Model weights
have separate terms: check the exact checkpoint's model card, license file and
revision before use or redistribution. The FunASR model agreement
applies only to models whose published terms adopt it, not every entry in this
catalogue. Third-party models, including OpenMOSS MOSS-Transcribe-Diarize, retain
their original authorship and model-specific licenses.
For model selection and deployment boundaries, start with the
Model Zoo guide and MOSS integration.
Model Zoo
Here we provided several pretrained models on different datasets. The details of models and datasets can be found on ModelScope.
Speech Recognition Models
Fun-ASR-Nano: choose the checkpoint for your interface
| Checkpoint |
Interface |
Scope |
| Fun-ASR-Nano-2512-hf |
Native Transformers 5.17.0, AutoProcessor + AutoModelForSpeechSeq2Seq |
Chinese, English, Japanese transcription; no remote Python code, native word timestamps or speaker identities |
| Fun-ASR-Nano-2512 |
FunASR toolkit AutoModel |
Original toolkit artifact; not interchangeable with the native export |
| Fun-ASR-Nano-2512-vllm |
Native vLLM |
Separate serving conversion and runtime |
| Fun-ASR-MLT-Nano-2512 |
FunASR toolkit |
Separate 31-language checkpoint, not the zh/en/ja native export |
Start with the native Transformers guide,
online Space, or
batch examples and notebook.
For a service, follow the deployment matrix.
Paraformer Models
| Model Name |
Language |
Training Data |
Vocab Size |
Parameter |
Offline/Online |
Notes |
| Paraformer-large |
CN & EN |
Alibaba Speech Data (60000hours) |
8404 |
220M |
Offline |
Duration of input wav <= 20s |
UniASR Models
Conformer Models
RNN-T Models
Multi-talker Speech Recognition Models
MFCCA Models
Voice Activity Detection Models
| Model Name |
Training Data |
Parameters |
Sampling Rate |
Notes |
| FSMN-VAD |
Alibaba Speech Data (5000hours) |
0.4M |
16000 |
|
Punctuation Restoration Models
| Model Name |
Training Data |
Parameters |
Vocab Size |
Offline/Online |
Notes |
| CT-Transformer |
Alibaba Text Data |
70M |
272727 |
Offline |
offline punctuation model |
Language Models
Speaker Verification Models
Speaker diarization Models
Third-party Unified Transcription and Diarization
| Model Name |
Publisher |
Parameters |
Notes |
| MOSS-Transcribe-Diarize |
OpenMOSS |
See official model card |
Third-party Apache-2.0 model. One offline request returns transcription, timestamps, and speaker labels; the FunASR integration does not require an external VAD service. See the deployment guide. |
Timestamp Prediction Models
