3bf986d08d
This PR adds support for non-streaming Zipformer CTC ASR models across multiple language bindings, WebAssembly, examples, and CI workflows. - Introduces a new OfflineZipformerCtcModelConfig in C/C++, Python, Swift, Java, Kotlin, Go, Dart, Pascal, and C# APIs - Updates initialization, freeing, and recognition logic to include Zipformer CTC in WASM and Node.js - Adds example scripts and CI steps for downloading, building, and running Zipformer CTC models Model doc is available at https://k2-fsa.github.io/sherpa/onnx/pretrained_models/offline-ctc/icefall/zipformer.html
Introduction
This folder contains examples for non-streaming ASR + voice activity detection with Dart API.
| File | Description |
|---|---|
| ./bin/paraformer.dart | Use a Paraformer model for speech recognition. See ./run-paraformer.sh |
| ./bin/sense-voice.dart | Use a SenseVoice Ctc model for speech recognition. See ./run-sense-voice-zh.sh and ./run-sense-voice-en.sh |
| ./bin/telespeech-ctc.dart | Use a TeleSpeech CTC model for speech recognition. See ./run-telespeech-ctc.sh |
| ./bin/whisper.dart | Use a Whisper model for speech recognition. See ./run-whisper.sh |
| ./bin/zipformer-transducer.dart | Use a Zipformer transducer model for speech recognition. See ./run-zipformer-transducer.sh |