paraformer-en

<div align="center">

Paraformer-en

A 220M offline, non-autoregressive English speech recognition model for 16 kHz audio.

Powered by FunASR. Follow the project or give it a star to receive new model, runtime, and deployment updates.

FunASR · Fun-ASR · SenseVoice · FunClip

</div>

Paraformer predicts output tokens in parallel instead of decoding them one by one. This checkpoint is intended for high-throughput English transcription where complete utterances or files are available before decoding.

Quick start

Install PyTorch and FunASR:

python -m pip install -U torch torchaudio funasr

For CUDA-specific PyTorch wheels, select the command for your platform in the PyTorch installation guide, then install funasr.

Run the audio example included in this repository:

from funasr import AutoModel

model = AutoModel(
    model="funasr/paraformer-en",
    hub="hf",
    device="cpu",  # Change to "cuda:0" for NVIDIA GPU inference.
)

audio = f"{model.model_path}/example/asr_example.wav"
result = model.generate(input=audio)
print(result[0]["text"])

Using the full repository ID is recommended. It selects this English checkpoint directly and avoids ambiguity with similarly named Paraformer models.

Long audio pipeline

Add voice activity detection to split long recordings and punctuation restoration to produce readable text:

from funasr import AutoModel

model = AutoModel(
    model="funasr/paraformer-en",
    hub="hf",
    vad_model="funasr/fsmn-vad",
    punc_model="funasr/ct-punc",
    device="cuda:0",
)

result = model.generate(
    input="meeting.wav",
    batch_size_s=300,
)
print(result[0]["text"])

The pipeline accepts common audio file paths and 16 kHz waveform input. Resample other sample rates to 16 kHz for predictable results.

OpenAI-compatible serving

Expose the model behind a local /v1/audio/transcriptions endpoint:

python -m pip install -U torch torchaudio funasr fastapi uvicorn python-multipart
funasr-server --model-path funasr/paraformer-en --hub hf --device cuda

curl http://localhost:8000/v1/audio/transcriptions \
  -F [email protected] \
  -F model=custom

funasr-server registers a checkpoint supplied through --model-path under the API model name custom.

See the OpenAI-compatible API examples, deployment matrix, and FunASR deployment hub for clients, containers, security guidance, and production topologies.

Model details

Artifact provenance

This Hugging Face repository mirrors the PyTorch checkpoint published as iic/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020 on ModelScope. It is not a TensorFlow 1.x Paraformer variant.

For reproducibility, the model.pt artifact in revision d043d60434a65ae49b2b2462a09660049871b8e9 has:

• size: 887,289,223 bytes
• SHA-256: e11203abf1f449b4c6515dee494c017ee27a4b716730378473d827ad3c7fe41c

Intended use and limitations

This model is suitable for offline English transcription, subtitle preparation, call or meeting processing, and batch speech pipelines. It is not a streaming checkpoint; use a streaming Paraformer model when partial low-latency results are required.

Recognition quality can degrade with heavy noise, overlapping speakers, strong accents, uncommon proper nouns, or domain-specific terminology. Validate accuracy on representative audio before production use, and review transcripts before using them in safety-critical or high-impact decisions.

Related models

Resources

• FunASR GitHub repository
• FunASR documentation
• Paraformer paper
• Issue tracker

Citation

@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}
}