* Don't reset model state and feature extractor on endpointing * support passing decoding_method from commandline * Add modified_beam_search to Python API * fix C API example * Fix style issues
Introduction
You can use sherpa-onnx-ffmpeg to decode a wav, mp3, or even a URL.
See https://github.com/ossrs/srs for more supported formats and protocols, e.g., RTMP/WebRTC/HLS/HTTP-FLV/SRT/MPEG-DASH/GB28181.
How to use
Please have a look at
./run.sh