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 directory contains examples for Dart API.
You can find the package at https://pub.dev/packages/sherpa_onnx
Description
| Directory | Description |
|---|---|
| ./speaker-diarization | Example for speaker diarization. |
| ./add-punctuations | Example for adding punctuations to text. |
| ./audio-tagging | Example for audio tagging. |
| ./keyword-spotter | Example for keyword spotting |
| ./non-streaming-asr | Example for non-streaming speech recognition |
| ./speaker-identification | Example for speaker identification and verification. |
| ./streaming-asr | Example for streaming speech recognition |
| ./tts | Example for text to speech |
| ./vad-with-non-streaming-asr | Example for voice activity detection with non-streaming speech recognition. You can use it to generate subtitles. |
| ./vad | Example for voice activity detection |
| ./speech-enhancement-gtcrn | Example for speech enhancement/denoising |
How to create an example in this folder
dart create vad
cd vad
# Edit pubspec.yaml and add sherpa_onnx to dependencies
dart pub get
dart run