speech recognition
Paraformer-zh (+ streaming)
Alibaba DAMO/Tongyi non-autoregressive ASR model.
Levelmodel
Classspeech recognition
Parameters220M
Contextnot in the notes
Released2022
Opennessopen weights restricted
Runs onCPU server, embedded GPU
Statusactive
R&D Topics
Identity
- Developer
- Alibaba (Qwen)
- Family
- not in the notes
- Released
- 2022 sourcesnotesunverified
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- other Non-autoregressive Paraformer
- Total parameters
- 220M sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- audio
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights restricted
- Licence
- FunASR Model Open Source License Agreement sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- CPU server, embedded GPU
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- Chinese/English with timestamps
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
DeveloperAlibaba (Qwen)big tech, China
Alibaba (Qwen)big tech, ChinaModelParaformer-zh (+ streaming)Alibaba (Qwen), speech recognition
Paraformer-zh (+ streaming)Alibaba (Qwen), speech recognitionR&D TopicsMassively Multilingual Speech RecognitionEfficient Acoustic Encoder Architectures for Speech Recognition
Use Casesnone recorded
Who Runs Itnone recorded
Organisations 1
R&D topics 2
Massively Multilingual Speech RecognitionTraining one speech recognition model on hundreds of thousands of hours or hundreds of la…produced byEfficient Acoustic Encoder Architectures for Speech RecognitionDesigning the convolution and attention blocks of speech recognition encoders to cut comp…produced by
Sources
- GitHub - modelscope/FunASR: Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diariza github.com https://github.com/modelscope/FunASR
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Paraformer-Zh (+ Streaming)", https://aurion.semai.id/models/alibaba-paraformer-zh/, records of October 2026.