Module asr

Module asr 

Source
Expand description

Automatic speech recognition

Structs§

Config
Configuration for a Model. See Model::from_pretrained for a simple way to get started.
Model
Streaming zipformer transducer speech recognition model.
OnlineStream
Context state for streaming speech recognition.
PhasedStream
A wrapper around multiple phase-shifted OnlineStream states. The use case is latency reduction at the cost of additional compute load.

Enums§

Arch