Commit Graph

  • 537e163dd0 WebAssembly example for VAD + Non-streaming ASR (#1284) Fangjun Kuang 2024-08-24 13:24:52 +08:00
  • 1ef8a7a202 Add WebAssembly for VAD (#1281) Fangjun Kuang 2024-08-23 17:08:37 +08:00
  • fb09f8fae3 Set batch size to 1 for more streaming ASR models (#1280) Fangjun Kuang 2024-08-23 11:06:55 +08:00
  • c61423ec5a Update wave-reader.cc (#1278) Malcolm Ke Win 2024-08-22 23:22:45 +08:00
  • 0e0d04a97a Provide models for mobile-only platforms by fixing batch size to 1 (#1276) Fangjun Kuang 2024-08-22 19:36:24 +08:00
  • d8001d6edc update kotlin api for better release native object and add user-friendly apis. (#1275) Robin Zhong 2024-08-22 19:18:11 +08:00
  • 5a2aa110b8 Text to speech API for Object Pascal. (#1273) Fangjun Kuang 2024-08-20 20:52:16 +08:00
  • e34a1a2aa3 Object pascal examples for recording and playing audio with portaudio. (#1271) Fangjun Kuang 2024-08-18 19:51:08 +08:00
  • f93f0ca94d Use a separate thread to initialize models for lazarus examples. (#1270) Fangjun Kuang 2024-08-18 14:59:48 +08:00
  • 8c087d9110 flutter: add lang, emotion, event to OfflineRecognizerResult (#1268) Emmanuel Schmidbauer 2024-08-16 19:21:59 -04:00
  • 88809753ab Release v1.10.22 (#1267) Fangjun Kuang 2024-08-16 22:40:49 +08:00
  • 9dcea49dba Fix looking up OOVs in lexicon.txt for MeloTTS models. (#1266) Fangjun Kuang 2024-08-16 22:10:03 +08:00
  • 63713ecbf0 Build generating subtitles APPs for more models (#1265) Fangjun Kuang 2024-08-16 20:11:24 +08:00
  • a3e98750e9 chore: update online-stream.h (#1264) Ikko Eltociear Ashimine 2024-08-16 16:17:15 +09:00
  • fbe35ba736 Add Lazarus example for generating subtitles using Silero VAD with non-streaming ASR (#1251) Fangjun Kuang 2024-08-15 22:19:45 +08:00
  • 97a6a2a16a Enable IPO only for Release build. (#1261) Fangjun Kuang 2024-08-15 18:16:42 +08:00
  • ca729faebf Support reading multi-channel wave files with 8/16/32-bit encoded samples (#1258) Fangjun Kuang 2024-08-15 14:54:43 +08:00
  • 62c4d4ab62 Add emotion, event of SenseVoice. (#1257) Robin Zhong 2024-08-14 15:50:13 +08:00
  • f300ec0f98 Add more C API examples (#1255) Han Zhu 2024-08-14 10:52:47 +08:00
  • 9f06b059d7 Update offline-recognizer.cc (#1253) ivan provalov 2024-08-13 08:04:51 -07:00
  • 619279b162 Pascal API for VAD (#1249) Fangjun Kuang 2024-08-13 16:16:51 +08:00
  • a7dc6c2c16 Pascal API for non-streaming ASR (#1247) Fangjun Kuang 2024-08-12 23:33:35 +08:00
  • 5791b695ea Pascal API for streaming ASR (#1246) Fangjun Kuang 2024-08-12 19:55:51 +08:00
  • 65f1c0fab2 Add Pascal API for reading wave files (#1243) Fangjun Kuang 2024-08-11 22:43:42 +08:00
  • 968623a477 Exclude .DS_Store files from flutter tts assets (#1238) Fangjun Kuang 2024-08-09 13:19:27 +08:00
  • 94e256244d Add blank penalty for various language bindings. (#1234) Fangjun Kuang 2024-08-08 10:43:31 +08:00
  • ba4cb6169f feat: addition of blank_penalty config in online_recognizer (#1232) Parth Khiera 2024-08-08 06:40:17 +05:30
  • 8a5f5c1999 Fix python two pass ASR examples (#1230) Fangjun Kuang 2024-08-07 18:35:38 +08:00
  • 1da75ee3c0 Fix typo in offline-lm-config.cc (#1229) xsjk 2024-08-07 15:38:34 +08:00
  • 9ee2943ed4 Add CI tests for online punctuation models (#1226) Fangjun Kuang 2024-08-06 18:10:30 +08:00
  • 375c055ff8 Fix style issues for online punctuation source files (#1225) Fangjun Kuang 2024-08-06 17:43:24 +08:00
  • 1414e4dc61 Add online punctuation and casing prediction model for English language (#1224) jianyou 2024-08-06 17:33:38 +08:00
  • 52830cc910 Add MeloTTS example for ios (#1223) Fangjun Kuang 2024-08-06 14:48:54 +08:00
  • 6422966a7f Support passing TTS callback in Swift API (#1218) Fangjun Kuang 2024-08-05 14:06:21 +08:00
  • 9caa488019 Fix setting SenseVoice language. (#1214) Fangjun Kuang 2024-08-04 19:02:23 +08:00
  • c2dce19140 Update README to include Rust. (#1212) Fangjun Kuang 2024-08-04 12:20:05 +08:00
  • d5f486878d Remove libonnxruntime_providers_cuda.so as a dependency. (#1210) Fangjun Kuang 2024-08-03 16:25:23 +08:00
  • 561d04dd92 describe how to add new words for MeloTTS models (#1209) Fangjun Kuang 2024-08-03 11:19:02 +08:00
  • 35c1b4a7a9 Add ReazonSpeech Japanese pre-trained model (#1203) Fangjun Kuang 2024-08-02 10:21:24 +08:00
  • 53484fcd9b Fix reading non-standard wav files. (#1199) Fangjun Kuang 2024-08-01 17:48:04 +08:00
  • ec98110e11 Add speaker identification and verification exmaple for Dart API (#1194) Fangjun Kuang 2024-07-31 13:53:52 +08:00
  • 963aaba82b Add Chinese+English tts example for flutter (#1192) Fangjun Kuang 2024-07-30 18:38:43 +08:00
  • c1b5fce01b Fix copying asset files for flutter examples. (#1191) Fangjun Kuang 2024-07-30 18:24:56 +08:00
  • 9e02f88dbb Non-streaming WebSocket client for Java. (#1190) Fangjun Kuang 2024-07-30 17:21:33 +08:00
  • 06fd50f536 Add test about whisper large-v3 for .Net (#1187) Fangjun Kuang 2024-07-29 20:49:38 +08:00
  • 86b4c9f535 Fix splitting sentences for MeloTTS (#1186) Fangjun Kuang 2024-07-29 17:04:45 +08:00
  • b1711ecaa1 Fix ffmpeg c api example (#1185) Fangjun Kuang 2024-07-29 14:27:55 +08:00
  • 646f99c870 Dart API for adding punctuations to text (#1182) Fangjun Kuang 2024-07-29 12:41:52 +08:00
  • cd1fedaa49 Add Dart API for audio tagging (#1181) Fangjun Kuang 2024-07-29 11:15:14 +08:00
  • 69b6b47d91 Add vad with non-streaming ASR examples for Dart API (#1180) Fangjun Kuang 2024-07-28 23:01:03 +08:00
  • d279c8d20e Add more Python examples for SenseVoice (#1179) Fangjun Kuang 2024-07-28 21:54:38 +08:00
  • 9e005f53c3 fix building MFC examples (#1178) Fangjun Kuang 2024-07-28 14:07:25 +08:00
  • 1f8e575133 Add TTS example for Java API. (#1176) Fangjun Kuang 2024-07-28 12:07:19 +08:00
  • 4e6aeff07e Refactor C API to prefix each API with SherpaOnnx. (#1171) Fangjun Kuang 2024-07-26 18:47:02 +08:00
  • 994c3e7c96 Add VAD + Non-streaming ASR example for JavaScript API. (#1170) Fangjun Kuang 2024-07-26 12:42:08 +08:00
  • 299f1a852b Fix style issues reported by clang-tidy (#1167) Fangjun Kuang 2024-07-23 09:26:36 +08:00
  • d32a46169f feat: add directml support (#1153) thewh1teagle 2024-07-22 18:50:48 +03:00
  • ea1d81bdfe C api example for sense voice (#1165) Fangjun Kuang 2024-07-22 16:54:00 +08:00
  • dd300b1de5 Add Java and Kotlin API for sense voice (#1164) Fangjun Kuang 2024-07-22 14:08:40 +08:00
  • ac8223bd8a Add Dart API for keyword spotter (#1162) Fangjun Kuang 2024-07-22 10:53:34 +08:00
  • 22a262f5e4 feat: add stt c api example (#1156) thewh1teagle 2024-07-22 05:32:12 +03:00
  • 1a471595a5 Fix Android build (#1161) Fangjun Kuang 2024-07-22 09:27:30 +08:00
  • ffdb23a8ec Add dart API for SenseVoice (#1159) Fangjun Kuang 2024-07-21 21:48:12 +08:00
  • 70d14353bb Add WebAssembly for SenseVoice (#1158) Fangjun Kuang 2024-07-21 15:39:55 +08:00
  • c3260ef842 Add JavaScript API for SenseVoice (#1157) Fangjun Kuang 2024-07-21 10:14:14 +08:00
  • 8f4d332aab Add Go API for SenseVoice (#1154) Fangjun Kuang 2024-07-20 23:41:53 +08:00
  • e472180f2c Add C# API for SenseVoice models (#1151) Fangjun Kuang 2024-07-20 17:09:23 +08:00
  • 25f0a10468 Add C++ runtime for SenseVoice models (#1148) Fangjun Kuang 2024-07-18 22:54:18 +08:00
  • 3bae5c3fe5 test exported sense voice models (#1147) Fangjun Kuang 2024-07-18 12:12:44 +08:00
  • 346f419f39 export sense-voice to onnx (#1144) Fangjun Kuang 2024-07-18 00:18:38 +08:00
  • 4198d9a166 Provide pre-built wheels with CUDA support. (#1143) Fangjun Kuang 2024-07-17 22:59:13 +08:00
  • 803c02db0a publish all pre-built wheels to huggingface (#1142) Fangjun Kuang 2024-07-17 14:41:27 +08:00
  • 9e448d03bc Provide npm package for 32-bit Windows x86 (#1141) Fangjun Kuang 2024-07-17 12:33:15 +08:00
  • 5b1fa8750f Fix hotwords OOV log (#1139) Wei Kang 2024-07-16 19:41:31 +08:00
  • 960eb7529e Add C++ runtime for MeloTTS (#1138) Fangjun Kuang 2024-07-16 15:55:02 +08:00
  • 95485411fa Support English for MeloTTS models. (#1134) Fangjun Kuang 2024-07-15 19:49:22 +08:00
  • fa07bbc176 Add APK for small paraformer (#1133) Fangjun Kuang 2024-07-15 19:44:36 +08:00
  • b2c283fa2b Add Swift API for adding punctuations to text. (#1132) Fangjun Kuang 2024-07-15 15:30:40 +08:00
  • 11cfd33b10 encoder only trt ep for transducer (#1130) Manickavela 2024-07-15 12:22:33 +05:30
  • c35200dccf Revert to onnxruntime 1.17.1 (#1131) Fangjun Kuang 2024-07-15 14:24:08 +08:00
  • 04c2319c2c Export MeloTTS to ONNX (#1129) Fangjun Kuang 2024-07-15 10:47:19 +08:00
  • de04b3b9bf Allow modify model config at decode time for ASR (#1124) ivan provalov 2024-07-13 07:30:47 -07:00
  • ab71c3976d Add int8 quantized whisper large models (#1126) Fangjun Kuang 2024-07-13 22:30:06 +08:00
  • 3951a12f8d Add pre-trained models for the Libriheavy dataset (#1122) Fangjun Kuang 2024-07-13 19:21:13 +08:00
  • b5093e27f9 Fix publishing apks to huggingface (#1121) Fangjun Kuang 2024-07-13 16:14:00 +08:00
  • 54e6e962bf Add microphone example for .Net keyword spotting (#1120) Fangjun Kuang 2024-07-13 14:56:39 +08:00
  • 4c626e89cf Fix releasing dart packages (#1117) Fangjun Kuang 2024-07-13 10:51:54 +08:00
  • 117cd7bb8c Support whisper large/large-v1/large-v2/large-v3 and distil-large-v2 (#1114) Fangjun Kuang 2024-07-12 23:47:39 +08:00
  • d928f77d0e Add timestamps about streaming models for Swift API (#1113) Fangjun Kuang 2024-07-12 17:39:46 +08:00
  • c0eaf86dbd feat: find best embedding matches (#1102) thewh1teagle 2024-07-11 04:38:06 +03:00
  • 1c104ea847 Update onnxruntime from v1.18.0 to v1.18.1 (#1107) Fangjun Kuang 2024-07-11 09:35:28 +08:00
  • 5a2603ff5c Handle invalid utf8 sequence from Whisper for Dart API. (#1106) Fangjun Kuang 2024-07-10 21:48:23 +08:00
  • 08c758520f Add keyword spotting for C# (#1105) Fangjun Kuang 2024-07-10 21:18:46 +08:00
  • dd0ff2ca06 Support onnxruntime 1.18.0 (#906) Fangjun Kuang 2024-07-10 17:05:26 +08:00
  • 9e446b8501 Fix typos (#1101) Fangjun Kuang 2024-07-09 20:08:47 +08:00
  • c2cc9dec58 Add Flush to VAD so that the last segment can be detected. (#1099) Fangjun Kuang 2024-07-09 16:15:56 +08:00
  • 3e4307e2fb updating trt workspace int64 (#1094) Manix 2024-07-08 18:08:16 +05:30
  • 4fd0493037 fix ios demo image for flutter tts (#1093) Fangjun Kuang 2024-07-08 17:07:01 +08:00
  • 5d2ceb3513 Support linux-arm64 for .Net (#1092) Fangjun Kuang 2024-07-08 16:13:51 +08:00
  • 02eab549a3 Fix windows build (#1091) Fangjun Kuang 2024-07-08 16:00:35 +08:00