icefall/egs/aishell/ASR/pruned_transducer_stateless7_streaming
Karel Vesely 716b82cc3a
streaming_decode.py, relax the audio range from [-1,+1] to [-10,+10] (#1448)
- some AudioTransform classes produce audio signals out of range [-1,+1]
   - Resample produced 1.0079
   - The range [-10,+10] was chosen to still be able to reliably
     distinguish from the [-32k,+32k] signal...
- this is related to : https://github.com/lhotse-speech/lhotse/issues/1254
2024-01-05 10:21:27 +08:00
..

This recipe implements Streaming Zipformer-Transducer model.

See https://k2-fsa.github.io/icefall/recipes/Streaming-ASR/librispeech/zipformer_transducer.html for detailed tutorials.

./emformer.py and ./train.py are basically the same as ./emformer2.py and ./do_not_use_it_directly.py. The only purpose of ./emformer2.py and ./do_not_use_it_directly.py is for exporting to sherpa-ncnn.