- Fix ffmpeg c api example (#1185)
- Fix splitting sentences for MeloTTS (#1186)
- Non-streaming WebSocket client for Java. (#1190)
- Fix copying asset files for flutter examples. (#1191)
- Add Chinese+English tts example for flutter (#1192)
- Add speaker identification and verification exmaple for Dart API (#1194)
- Fix reading non-standard wav files. (#1199)
- Add ReazonSpeech Japanese pre-trained model (#1203)
- Describe how to add new words for MeloTTS models (#1209)
- Remove libonnxruntime_providers_cuda.so as a dependency. (#1210)
- Fix setting SenseVoice language. (#1214)
- Support passing TTS callback in Swift API (#1218)
- Add MeloTTS example for ios (#1223)
- Add online punctuation and casing prediction model for English language (#1224)
- Fix python two pass ASR examples (#1230)
- Add blank penalty for various language bindings
- Add Dart API for audio tagging
- Add Dart API for adding punctuations to text
- Prefix all C API functions with SherpaOnnx
- Fix the case when recognition results contain the symbol
"
. It caused issues when converting results to a json string.
- Support SenseVoice CTC models.
- Add Dart API for keyword spotter.
- Support zh-en TTS model from MeloTTS.
- Downgrade onnxruntime from v1.18.1 to v1.17.1
- Support whisper large v3
- Update onnxruntime from v1.18.0 to v1.18.1
- Fix invalid utf8 sequence from Whisper for Dart API.
- Update onnxruntime from 1.17.1 to 1.18.0
- Add C# API for Keyword spotting
- Add Flush to VAD so that the last speech segment can be detected. See also k2-fsa#1077 (reply in thread)
- Support the iOS platform for Flutter.
- Build sherpa-onnx into a single shared library.
- Fix released packages. piper-phonemize was not included in v1.10.8.
- Fix released packages. There should be a lib directory.
- Support Android for Flutter.
- Fix passing C# string to C++
- Enable to stop TTS generation
- Add inverse text normalization
- Add TTS
- Publish with CI
- Fix path separator on Windows.
- Support specifying lib path.
- Initial release.