Online transducer models

This section lists available online transducer models.

• Zipformer-transducer-based Models
  • sherpa-onnx-streaming-zipformer-korean-2024-06-16 (Korean)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
  • sherpa-onnx-streaming-zipformer-multi-zh-hans-2023-12-12 (Chinese)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
  • k2-fsa/icefall-asr-zipformer-wenetspeech-streaming-small (Chinese)
    • Download the model
  • k2-fsa/icefall-asr-zipformer-wenetspeech-streaming-large (Chinese)
    • Download the model
  • pkufool/icefall-asr-zipformer-streaming-wenetspeech-20230615 (Chinese)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
  • csukuangfj/sherpa-onnx-streaming-zipformer-en-2023-06-26 (English)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
  • csukuangfj/sherpa-onnx-streaming-zipformer-en-2023-06-21 (English)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
  • csukuangfj/sherpa-onnx-streaming-zipformer-en-2023-02-21 (English)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
  • csukuangfj/sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20 (Bilingual, Chinese + English)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
  • shaojieli/sherpa-onnx-streaming-zipformer-fr-2023-04-14 (French)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
  • sherpa-onnx-streaming-zipformer-small-bilingual-zh-en-2023-02-16 (Bilingual, Chinese + English)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
  • csukuangfj/sherpa-onnx-streaming-zipformer-zh-14M-2023-02-23 (Chinese)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
  • csukuangfj/sherpa-onnx-streaming-zipformer-en-20M-2023-02-17 (English)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
• Conformer-transducer-based Models
  • csukuangfj/sherpa-onnx-streaming-conformer-zh-2023-05-23 (Chinese)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
• LSTM-transducer-based Models
  • csukuangfj/sherpa-onnx-lstm-en-2023-02-17 (English)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone
  • csukuangfj/sherpa-onnx-lstm-zh-2023-02-20 (Chinese)
    • Download the model
    • Decode a single wave file
      • fp32
      • int8
    • Real-time speech recognition from a microphone