v1.10.22

What's Changed

• Exclude .DS_Store files from flutter tts assets by @csukuangfj in #1238
• Add Pascal API for reading wave files by @csukuangfj in #1243
• Pascal API for streaming ASR by @csukuangfj in #1246
• Pascal API for non-streaming ASR by @csukuangfj in #1247
• Pascal API for VAD by @csukuangfj in #1249
• Update offline-recognizer.cc by @iprovalo in #1253
• Add more C API examples by @zhu-han in #1255
• Add emotion, event of SenseVoice. by @fbzhong in #1257
• Support reading multi-channel wave files with 8/16/32-bit encoded samples by @csukuangfj in #1258
• Enable IPO only for Release build. by @csukuangfj in #1261
• Add Lazarus example for generating subtitles using Silero VAD with non-streaming ASR by @csukuangfj in #1251
• chore: update online-stream.h by @eltociear in #1264
• Build generating subtitles APPs for more models by @csukuangfj in #1265
• Fix looking up OOVs in lexicon.txt for MeloTTS models. by @csukuangfj in #1266
• Release v1.10.22 by @csukuangfj in #1267

New Contributors

• @zhu-han made their first contribution in #1255
• @fbzhong made their first contribution in #1257

Full Changelog: v1.10.21...v1.10.22

v1.10.21

What's Changed

• Fix ffmpeg c api example by @csukuangfj in #1185
• Fix splitting sentences for MeloTTS by @csukuangfj in #1186
• Add test about whisper large-v3 for .Net by @csukuangfj in #1187
• Non-streaming WebSocket client for Java. by @csukuangfj in #1190
• Fix copying asset files for flutter examples. by @csukuangfj in #1191
• Add Chinese+English tts example for flutter by @csukuangfj in #1192
• Add speaker identification and verification exmaple for Dart API by @csukuangfj in #1194
• Fix reading non-standard wav files. by @csukuangfj in #1199
• Add ReazonSpeech Japanese pre-trained model by @csukuangfj in #1203
• describe how to add new words for MeloTTS models by @csukuangfj in #1209
• Remove libonnxruntime_providers_cuda.so as a dependency. by @csukuangfj in #1210
• Update README to include Rust. by @csukuangfj in #1212
• Fix setting SenseVoice language. by @csukuangfj in #1214
• Support passing TTS callback from Swift to C by @csukuangfj in #1218
• Add MeloTTS example for ios by @csukuangfj in #1223
• Add online punctuation and casing prediction model for English language by @frankyoujian in #1224
• Fix style issues for online punctuation source files by @csukuangfj in #1225
• Add CI tests for online punctuation models by @csukuangfj in #1226
• Fix typo in offline-lm-config.cc by @xsjk in #1229
• Fix Python two pass ASR examples by @csukuangfj in #1230
• addition of blank_penalty config in online_recognizer by @parth-khiera in #1232
• Add blank penalty for various language bindings. by @csukuangfj in #1234

New Contributors

• @xsjk made their first contribution in #1229
• @parth-khiera made their first contribution in #1232

Full Changelog: v1.10.20...v1.10.21

v1.10.20

What's Changed

• Add TTS example for Java API. by @csukuangfj in #1176
• fix building MFC examples by @csukuangfj in #1178
• Add more Python examples for SenseVoice by @csukuangfj in #1179
• Add vad with non-streaming ASR examples for Dart API by @csukuangfj in #1180
• Add Dart API for audio tagging by @csukuangfj in #1181
• Dart API for adding punctuations to text by @csukuangfj in #1182

Full Changelog: v1.10.19...v1.10.20

v1.10.19

What's Changed

• Refactor C API to prefix each API with SherpaOnnx. by @csukuangfj in #1171

Full Changelog: v1.10.18...v1.10.19

v1.10.18

What's Changed

• Add VAD + Non-streaming ASR example for JavaScript API. by @csukuangfj in #1170

Full Changelog: v1.10.17...v1.10.18

v1.10.17

Full Changelog: v1.10.17...v1.10.17

What's Changed

• Fix hotwords OOV log by @pkufool in #1139
• Provide npm package for 32-bit Windows x86 by @csukuangfj in #1141
• publish all pre-built wheels to huggingface by @csukuangfj in #1142
• Provide pre-built wheels with CUDA support. by @csukuangfj in #1143
• export sense-voice to onnx by @csukuangfj in #1144
• test exported sense voice models by @csukuangfj in #1147
• Add C++ runtime for SenseVoice models by @csukuangfj in #1148
• Add C# API for SenseVoice models by @csukuangfj in #1151
• Add Go API for SenseVoice by @csukuangfj in #1154
• Add JavaScript API for SenseVoice by @csukuangfj in #1157
• Add WebAssembly for SenseVoice by @csukuangfj in #1158
• Add dart API for SenseVoice by @csukuangfj in #1159
• Fix Android build by @csukuangfj in #1161
• feat: add stt c api example by @thewh1teagle in #1156
• Add Dart API for keyword spotter by @csukuangfj in #1162
• Add Java and Kotlin API for sense voice by @csukuangfj in #1164
• C api example for sense voice by @csukuangfj in #1165
• feat: add directml support by @thewh1teagle in #1153
• Fix style issues reported by clang-tidy by @csukuangfj in #1167

Full Changelog: v1.10.16...v1.10.17

v1.10.16

What's Changed

• encoder only trt ep for transducer by @manickavela29 in #1130
• Add Swift API for adding punctuations to text. by @csukuangfj in #1132
• Add APK for small paraformer by @csukuangfj in #1133
• Support English for MeloTTS models. by @csukuangfj in #1134
• Add C++ runtime for MeloTTS by @csukuangfj in #1138

Full Changelog: v1.10.15...v1.10.16

v1.10.15

What's Changed

• Fix releasing dart packages by @csukuangfj in #1117
• Add microphone example for .Net keyword spotting by @csukuangfj in #1120
• Fix publishing apks to huggingface by @csukuangfj in #1121
• Add pre-trained models for the Libriheavy dataset by @csukuangfj in #1122
• Add int8 quantized whisper large models by @csukuangfj in #1126
• Allow modify model config at decode time for ASR by @iprovalo in #1124
• Export MeloTTS to ONNX by @csukuangfj in #1129
• Revert to onnxruntime 1.17.1 by @csukuangfj in #1131

New Contributors

• @iprovalo made their first contribution in #1124

Full Changelog: v1.10.14...v1.10.15

v1.10.14

What's Changed

• Add keyword spotting for C# by @csukuangfj in #1105
• Handle invalid utf8 sequence from Whisper for Dart API. by @csukuangfj in #1106
• Update onnxruntime from v1.18.0 to v1.18.1 by @csukuangfj in #1107
• feat: find best embedding matches by @thewh1teagle in #1102
• Add timestamps about streaming models for Swift API by @csukuangfj in #1113
• Support whisper large/large-v1/large-v2/large-v3 and distil-large-v2 by @csukuangfj in #1114

New Contributors

• @thewh1teagle made their first contribution in #1102

Full Changelog: v1.10.13...v1.10.14

v1.10.13

Support onnxruntime 1.18.0 (#906)