EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
16
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
This repository has been archived on 2025-08-26. You can view files and clone it, but cannot push or open issues or pull requests.
Files
2e45d327a50ef0ae16c2619a028ced0e872c5361
enginex-mr_series-sherpa-onnx/sherpa-onnx/csrc
History
Karel Vesely 2e45d327a5 Adding temperature scaling on Joiner logits: (#789) 
* Adding temperature scaling on Joiner logits:

- T hard-coded to 2.0
- so far best result NCE 0.122 (still not so high)
    - the BPE scores were rescaled with 0.2 (but then also incorrect words
      get high confidence, visually reasonable histograms are for 0.5 scale)
    - BPE->WORD score merging done by min(.) function
      (tried also prob-product, and also arithmetic, geometric, harmonic mean)

- without temperature scaling (i.e. scale 1.0), the best NCE was 0.032 (here product merging was best)

Results seem consistent with: https://arxiv.org/abs/2110.15222

Everything tuned on a very-small set of 100 sentences with 813 words and 10.2% WER, a Czech model.

I also experimented with blank posteriors mixed into the BPE confidences,
but no NCE improvement found, so not pushing that.

Temperature scling added also to the Greedy search confidences.

* making `temperature_scale` configurable from outside
2024-04-26 09:44:26 +08:00
..
.gitignore
Add Android demo for speaker recognition (#536)
2024-01-23 16:50:52 +08:00
alsa-play.cc
Play generated audio using alsa for TTS (#482)
2023-12-13 22:28:03 +08:00
alsa-play.h
Play generated audio using alsa for TTS (#482)
2023-12-13 22:28:03 +08:00
alsa.cc
Add C++ microphone examples for audio tagging (#749)
2024-04-10 21:00:35 +08:00
alsa.h
Support cross compiling for aarch64 (#52)
2023-02-21 22:04:21 +08:00
audio-tagging-ced-impl.h
Support CED models (#792)
2024-04-19 15:20:37 +08:00
audio-tagging-impl.cc
Support CED models (#792)
2024-04-19 15:20:37 +08:00
audio-tagging-impl.h
Add Kotlin API for audio tagging (#770)
2024-04-15 13:49:35 +08:00
audio-tagging-label-file.cc
Add Kotlin API for audio tagging (#770)
2024-04-15 13:49:35 +08:00
audio-tagging-label-file.h
Add Kotlin API for audio tagging (#770)
2024-04-15 13:49:35 +08:00
audio-tagging-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
audio-tagging-model-config.h
Support CED models (#792)
2024-04-19 15:20:37 +08:00
audio-tagging-zipformer-impl.h
Support CED models (#792)
2024-04-19 15:20:37 +08:00
audio-tagging.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
audio-tagging.h
Add Kotlin API for audio tagging (#770)
2024-04-15 13:49:35 +08:00
base64-decode.cc
Support whisper models (#238)
2023-08-07 12:34:18 +08:00
base64-decode.h
Support whisper models (#238)
2023-08-07 12:34:18 +08:00
cat-test.cc
Add Streaming zipformer (#50)
2023-02-21 20:00:03 +08:00
cat.cc
Use deep copy in Clone() (#66)
2023-02-26 14:54:01 +08:00
cat.h
Add Streaming zipformer (#50)
2023-02-21 20:00:03 +08:00
circular-buffer-test.cc
Add Silero VAD (#313)
2023-09-17 14:54:38 +08:00
circular-buffer.cc
Resize circular buffer on overflow (#422)
2023-11-13 12:07:51 +08:00
circular-buffer.h
Resize circular buffer on overflow (#422)
2023-11-13 12:07:51 +08:00
CMakeLists.txt
Add jieba for Chinese TTS models (#797)
2024-04-21 14:47:13 +08:00
context-graph-test.cc
decoder for open vocabulary keyword spotting (#505)
2024-01-20 22:52:41 +08:00
context-graph.cc
decoder for open vocabulary keyword spotting (#505)
2024-01-20 22:52:41 +08:00
context-graph.h
decoder for open vocabulary keyword spotting (#505)
2024-01-20 22:52:41 +08:00
cppjieba-test.cc
Add jieba for Chinese TTS models (#797)
2024-04-21 14:47:13 +08:00
CPPLINT.cfg
add streaming websocket server and client (#62)
2023-02-24 21:39:51 +08:00
display.h
Code refactoring (#74)
2023-03-03 12:10:59 +08:00
endpoint.cc
Add endpointing (#54)
2023-02-22 15:35:55 +08:00
endpoint.h
Add endpointing (#54)
2023-02-22 15:35:55 +08:00
features.cc
Support CED models (#792)
2024-04-19 15:20:37 +08:00
features.h
Configurable low_freq high_freq, dithering (#664)
2024-03-22 21:41:44 +08:00
file-utils.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
file-utils.h
add streaming websocket server and client (#62)
2023-02-24 21:39:51 +08:00
hypothesis.cc
Add lm decode for the Python API. (#353)
2023-10-13 11:15:16 +08:00
hypothesis.h
Track token scores (#571)
2024-02-29 06:28:45 +08:00
jieba-lexicon.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
jieba-lexicon.h
Add jieba for Chinese TTS models (#797)
2024-04-21 14:47:13 +08:00
keyword-spotter-impl.cc
decoder for open vocabulary keyword spotting (#505)
2024-01-20 22:52:41 +08:00
keyword-spotter-impl.h
decoder for open vocabulary keyword spotting (#505)
2024-01-20 22:52:41 +08:00
keyword-spotter-transducer-impl.h
Configurable low_freq high_freq, dithering (#664)
2024-03-22 21:41:44 +08:00
keyword-spotter.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
keyword-spotter.h
decoder for open vocabulary keyword spotting (#505)
2024-01-20 22:52:41 +08:00
lexicon.cc
Add jieba for Chinese TTS models (#797)
2024-04-21 14:47:13 +08:00
lexicon.h
Support heteronyms in Chinese TTS (#738)
2024-04-08 11:01:30 +08:00
log.cc
Add endpointing (#54)
2023-02-22 15:35:55 +08:00
log.h
Add endpointing (#54)
2023-02-22 15:35:55 +08:00
macros.h
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
math.h
Support audio tagging using zipformer (#747)
2024-04-10 14:47:06 +08:00
microphone.cc
add portaudio for reading microphones (#55)
2023-02-22 17:13:07 +08:00
microphone.h
add portaudio for reading microphones (#55)
2023-02-22 17:13:07 +08:00
offline-ced-model.cc
Support CED models (#792)
2024-04-19 15:20:37 +08:00
offline-ced-model.h
Support CED models (#792)
2024-04-19 15:20:37 +08:00
offline-ct-transformer-model-meta-data.h
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
offline-ct-transformer-model.cc
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
offline-ct-transformer-model.h
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
offline-ctc-decoder.h
Begin to support CTC models (#119)
2023-04-07 23:11:34 +08:00
offline-ctc-fst-decoder-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
offline-ctc-fst-decoder-config.h
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
offline-ctc-fst-decoder.cc
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
offline-ctc-fst-decoder.h
Add CTC HLG decoding using OpenFst (#349)
2023-10-08 11:32:39 +08:00
offline-ctc-greedy-search-decoder.cc
Begin to support CTC models (#119)
2023-04-07 23:11:34 +08:00
offline-ctc-greedy-search-decoder.h
Begin to support CTC models (#119)
2023-04-07 23:11:34 +08:00
offline-ctc-model.cc
Use a single thread when loading models (#703)
2024-03-26 13:35:33 +08:00
offline-ctc-model.h
Support non-streaming WeNet CTC models. (#426)
2023-11-15 14:23:20 +08:00
offline-lm-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
offline-lm-config.h
RNNLM model support lm_num_thread and lm_provider setting (#173)
2023-06-12 15:51:27 +08:00
offline-lm.cc
Add two-pass speech recognition Android/iOS demo (#304)
2023-09-12 15:40:16 +08:00
offline-lm.h
Add two-pass speech recognition Android/iOS demo (#304)
2023-09-12 15:40:16 +08:00
offline-model-config.cc
Support non-streaming WeNet CTC models. (#426)
2023-11-15 14:23:20 +08:00
offline-model-config.h
Support non-streaming WeNet CTC models. (#426)
2023-11-15 14:23:20 +08:00
offline-nemo-enc-dec-ctc-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
offline-nemo-enc-dec-ctc-model-config.h
Begin to support CTC models (#119)
2023-04-07 23:11:34 +08:00
offline-nemo-enc-dec-ctc-model.cc
Add CTC HLG decoding using OpenFst (#349)
2023-10-08 11:32:39 +08:00
offline-nemo-enc-dec-ctc-model.h
Add CTC HLG decoding using OpenFst (#349)
2023-10-08 11:32:39 +08:00
offline-paraformer-decoder.h
Add timestamps for offline paraformer (#310)
2023-09-14 19:33:41 +08:00
offline-paraformer-greedy-search-decoder.cc
Add timestamps for offline paraformer (#310)
2023-09-14 19:33:41 +08:00
offline-paraformer-greedy-search-decoder.h
Add timestamps for offline paraformer (#310)
2023-09-14 19:33:41 +08:00
offline-paraformer-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
offline-paraformer-model-config.h
Support paraformer. (#95)
2023-03-28 17:59:54 +08:00
offline-paraformer-model.cc
Add timestamps for offline paraformer (#310)
2023-09-14 19:33:41 +08:00
offline-paraformer-model.h
Add timestamps for offline paraformer (#310)
2023-09-14 19:33:41 +08:00
offline-punctuation-ct-transformer-impl.h
Add C API for punctuation (#768)
2024-04-14 19:02:34 +08:00
offline-punctuation-impl.cc
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
offline-punctuation-impl.h
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
offline-punctuation-model-config.cc
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
offline-punctuation-model-config.h
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
offline-punctuation.cc
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
offline-punctuation.h
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
offline-recognizer-ctc-impl.h
Fixes issue #535 , fix hexa 1-char tokens in ASR output. (#550)
2024-01-26 19:23:20 +08:00
offline-recognizer-impl.cc
Use a single thread when loading models (#703)
2024-03-26 13:35:33 +08:00
offline-recognizer-impl.h
Refactor hotwords，support loading hotwords from file (#296)
2023-09-14 19:33:17 +08:00
offline-recognizer-paraformer-impl.h
Add timestamps for offline paraformer (#310)
2023-09-14 19:33:41 +08:00
offline-recognizer-transducer-impl.h
Fix code style issues (#774)
2024-04-16 09:46:15 +08:00
offline-recognizer-whisper-impl.h
Support spoken language identification with whisper (#694)
2024-03-24 22:57:00 +08:00
offline-recognizer.cc
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
offline-recognizer.h
add blank_penalty for offline transducer (#542)
2024-01-25 15:00:09 +08:00
offline-rnn-lm.cc
Add two-pass speech recognition Android/iOS demo (#304)
2023-09-12 15:40:16 +08:00
offline-rnn-lm.h
Add two-pass speech recognition Android/iOS demo (#304)
2023-09-12 15:40:16 +08:00
offline-stream.cc
Support CED models (#792)
2024-04-19 15:20:37 +08:00
offline-stream.h
Support CED models (#792)
2024-04-19 15:20:37 +08:00
offline-tdnn-ctc-model.cc
Add CTC HLG decoding using OpenFst (#349)
2023-10-08 11:32:39 +08:00
offline-tdnn-ctc-model.h
Add CTC HLG decoding using OpenFst (#349)
2023-10-08 11:32:39 +08:00
offline-tdnn-model-config.cc
Support TDNN models from the yesno recipe from icefall (#262)
2023-08-12 19:50:22 +08:00
offline-tdnn-model-config.h
Support TDNN models from the yesno recipe from icefall (#262)
2023-08-12 19:50:22 +08:00
offline-transducer-decoder.h
Implement context biasing with a Aho Corasick automata (#145)
2023-06-16 14:26:36 +08:00
offline-transducer-greedy-search-decoder.cc
add blank_penalty for offline transducer (#542)
2024-01-25 15:00:09 +08:00
offline-transducer-greedy-search-decoder.h
Fix code style issues (#774)
2024-04-16 09:46:15 +08:00
offline-transducer-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
offline-transducer-model-config.h
Support paraformer. (#95)
2023-03-28 17:59:54 +08:00
offline-transducer-model.cc
Add two-pass speech recognition Android/iOS demo (#304)
2023-09-12 15:40:16 +08:00
offline-transducer-model.h
Add two-pass speech recognition Android/iOS demo (#304)
2023-09-12 15:40:16 +08:00
offline-transducer-modified-beam-search-decoder.cc
add blank_penalty for offline transducer (#542)
2024-01-25 15:00:09 +08:00
offline-transducer-modified-beam-search-decoder.h
add blank_penalty for offline transducer (#542)
2024-01-25 15:00:09 +08:00
offline-tts-character-frontend.cc
Support Ukrainian VITS models from coqui-ai/TTS (#469)
2023-12-06 19:37:11 +08:00
offline-tts-character-frontend.h
Support Ukrainian VITS models from coqui-ai/TTS (#469)
2023-12-06 19:37:11 +08:00
offline-tts-frontend.h
Use piper-phonemize to convert text to token IDs (#453)
2023-11-30 23:57:43 +08:00
offline-tts-impl.cc
Add jni interface and kotlin API examples for TTS. (#381)
2023-10-23 12:31:54 +08:00
offline-tts-impl.h
Replace Android system TTS engine (#508)
2023-12-31 23:02:35 +08:00
offline-tts-model-config.cc
Add TTS with VITS (#360)
2023-10-13 19:30:38 +08:00
offline-tts-model-config.h
Add TTS with VITS (#360)
2023-10-13 19:30:38 +08:00
offline-tts-vits-impl.h
Add jieba for Chinese TTS models (#797)
2024-04-21 14:47:13 +08:00
offline-tts-vits-model-config.cc
Refactor the JNI interface to make it more modular and maintainable (#802)
2024-04-24 09:48:42 +08:00
offline-tts-vits-model-config.h
Add jieba for Chinese TTS models (#797)
2024-04-21 14:47:13 +08:00
offline-tts-vits-model-metadata.h
Add jieba for Chinese TTS models (#797)
2024-04-21 14:47:13 +08:00
offline-tts-vits-model.cc
Add jieba for Chinese TTS models (#797)
2024-04-21 14:47:13 +08:00
offline-tts-vits-model.h
Use espeak-ng for coqui-ai/TTS VITS English models. (#466)
2023-12-06 11:00:38 +08:00
offline-tts.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
offline-tts.h
Support heteronyms in Chinese TTS (#738)
2024-04-08 11:01:30 +08:00
offline-websocket-server-impl.cc
Fix code style issues (#774)
2024-04-16 09:46:15 +08:00
offline-websocket-server-impl.h
add offline websocket server/client (#98)
2023-03-29 21:48:45 +08:00
offline-websocket-server.cc
add python tests (#111)
2023-04-02 23:05:30 +08:00
offline-wenet-ctc-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
offline-wenet-ctc-model-config.h
Support non-streaming WeNet CTC models. (#426)
2023-11-15 14:23:20 +08:00
offline-wenet-ctc-model.cc
Support non-streaming WeNet CTC models. (#426)
2023-11-15 14:23:20 +08:00
offline-wenet-ctc-model.h
Support non-streaming WeNet CTC models. (#426)
2023-11-15 14:23:20 +08:00
offline-whisper-decoder.h
Support whisper models (#238)
2023-08-07 12:34:18 +08:00
offline-whisper-greedy-search-decoder.cc
Support spoken language identification with whisper (#694)
2024-03-24 22:57:00 +08:00
offline-whisper-greedy-search-decoder.h
Support spoken language identification with whisper (#694)
2024-03-24 22:57:00 +08:00
offline-whisper-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
offline-whisper-model-config.h
Remove the 30-second constraint from whisper. (#471)
2023-12-07 17:47:08 +08:00
offline-whisper-model.cc
Add Android demo for spoken language identification using Whisper multilingual models (#783)
2024-04-18 14:33:59 +08:00
offline-whisper-model.h
Add Android demo for spoken language identification using Whisper multilingual models (#783)
2024-04-18 14:33:59 +08:00
offline-zipformer-audio-tagging-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
offline-zipformer-audio-tagging-model-config.h
Support audio tagging using zipformer (#747)
2024-04-10 14:47:06 +08:00
offline-zipformer-audio-tagging-model.cc
Support audio tagging using zipformer (#747)
2024-04-10 14:47:06 +08:00
offline-zipformer-audio-tagging-model.h
Support audio tagging using zipformer (#747)
2024-04-10 14:47:06 +08:00
offline-zipformer-ctc-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
offline-zipformer-ctc-model-config.h
Add CTC HLG decoding using OpenFst (#349)
2023-10-08 11:32:39 +08:00
offline-zipformer-ctc-model.cc
Support audio tagging using zipformer (#747)
2024-04-10 14:47:06 +08:00
offline-zipformer-ctc-model.h
Support audio tagging using zipformer (#747)
2024-04-10 14:47:06 +08:00
online-conformer-transducer-model.cc
Refactor online recognizer (#250)
2023-08-09 20:27:31 +08:00
online-conformer-transducer-model.h
Refactor online recognizer (#250)
2023-08-09 20:27:31 +08:00
online-ctc-decoder.h
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
online-ctc-fst-decoder-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
online-ctc-fst-decoder-config.h
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
online-ctc-fst-decoder.cc
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
online-ctc-fst-decoder.h
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
online-ctc-greedy-search-decoder.cc
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
online-ctc-greedy-search-decoder.h
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
online-ctc-model.cc
Support streaming zipformer CTC (#496)
2023-12-22 13:46:33 +08:00
online-ctc-model.h
Support streaming zipformer CTC (#496)
2023-12-22 13:46:33 +08:00
online-lm-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
online-lm-config.h
Fix code style issues (#774)
2024-04-16 09:46:15 +08:00
online-lm.cc
RNNLM model support lm_num_thread and lm_provider setting (#173)
2023-06-12 15:51:27 +08:00
online-lm.h
RNNLM model support lm_num_thread and lm_provider setting (#173)
2023-06-12 15:51:27 +08:00
online-lstm-transducer-model.cc
Refactor online recognizer (#250)
2023-08-09 20:27:31 +08:00
online-lstm-transducer-model.h
Refactor online recognizer (#250)
2023-08-09 20:27:31 +08:00
online-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
online-model-config.h
Fix code style issues (#774)
2024-04-16 09:46:15 +08:00
online-paraformer-decoder.h
Support streaming paraformer (#263)
2023-08-14 10:32:14 +08:00
online-paraformer-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
online-paraformer-model-config.h
Support streaming paraformer (#263)
2023-08-14 10:32:14 +08:00
online-paraformer-model.cc
Support streaming paraformer (#263)
2023-08-14 10:32:14 +08:00
online-paraformer-model.h
Support streaming paraformer (#263)
2023-08-14 10:32:14 +08:00
online-recognizer-ctc-impl.h
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
online-recognizer-impl.cc
Support streaming zipformer CTC (#496)
2023-12-22 13:46:33 +08:00
online-recognizer-impl.h
Adding warm up for Zipformer2 (#766)
2024-04-16 09:16:55 +08:00
online-recognizer-paraformer-impl.h
Increase the right chunk size of streaming paraformer to 3 (#588)
2024-02-20 09:44:40 +08:00
online-recognizer-transducer-impl.h
Adding temperature scaling on Joiner logits: (#789)
2024-04-26 09:44:26 +08:00
online-recognizer.cc
Adding temperature scaling on Joiner logits: (#789)
2024-04-26 09:44:26 +08:00
online-recognizer.h
Adding temperature scaling on Joiner logits: (#789)
2024-04-26 09:44:26 +08:00
online-rnn-lm.cc
Fix code style issues (#774)
2024-04-16 09:46:15 +08:00
online-rnn-lm.h
RNNLM model support lm_num_thread and lm_provider setting (#173)
2023-06-12 15:51:27 +08:00
online-stream.cc
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
online-stream.h
Add HLG decoding for streaming CTC models (#731)
2024-04-03 21:31:42 +08:00
online-transducer-decoder.cc
Track token scores (#571)
2024-02-29 06:28:45 +08:00
online-transducer-decoder.h
Track token scores (#571)
2024-02-29 06:28:45 +08:00
online-transducer-greedy-search-decoder.cc
Adding temperature scaling on Joiner logits: (#789)
2024-04-26 09:44:26 +08:00
online-transducer-greedy-search-decoder.h
Adding temperature scaling on Joiner logits: (#789)
2024-04-26 09:44:26 +08:00
online-transducer-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
online-transducer-model-config.h
Refactor online recognizer (#250)
2023-08-09 20:27:31 +08:00
online-transducer-model.cc
Use a single thread when loading models (#703)
2024-03-26 13:35:33 +08:00
online-transducer-model.h
Fix code style issues (#774)
2024-04-16 09:46:15 +08:00
online-transducer-modified-beam-search-decoder.cc
Adding temperature scaling on Joiner logits: (#789)
2024-04-26 09:44:26 +08:00
online-transducer-modified-beam-search-decoder.h
Adding temperature scaling on Joiner logits: (#789)
2024-04-26 09:44:26 +08:00
online-websocket-client.cc
Refactor Java API (#806)
2024-04-24 18:41:48 +08:00
online-websocket-server-impl.cc
Adding warm up for Zipformer2 (#766)
2024-04-16 09:16:55 +08:00
online-websocket-server-impl.h
Adding warm up for Zipformer2 (#766)
2024-04-16 09:16:55 +08:00
online-websocket-server.cc
add offline websocket server/client (#98)
2023-03-29 21:48:45 +08:00
online-wenet-ctc-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
online-wenet-ctc-model-config.h
Support streaming conformer CTC models from wenet (#427)
2023-11-16 10:35:23 +08:00
online-wenet-ctc-model.cc
Support streaming zipformer CTC (#496)
2023-12-22 13:46:33 +08:00
online-wenet-ctc-model.h
Support streaming zipformer CTC (#496)
2023-12-22 13:46:33 +08:00
online-zipformer2-ctc-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
online-zipformer2-ctc-model-config.h
Support streaming zipformer CTC (#496)
2023-12-22 13:46:33 +08:00
online-zipformer2-ctc-model.cc
Add WebAssembly for ASR (#604)
2024-02-23 17:39:11 +08:00
online-zipformer2-ctc-model.h
Support streaming zipformer CTC (#496)
2023-12-22 13:46:33 +08:00
online-zipformer2-transducer-model.cc
Configurable low_freq high_freq, dithering (#664)
2024-03-22 21:41:44 +08:00
online-zipformer2-transducer-model.h
Add timestamps and tokens for .Net's online models. (#690)
2024-03-23 18:51:56 +08:00
online-zipformer-transducer-model.cc
Add WebAssembly for ASR (#604)
2024-02-23 17:39:11 +08:00
online-zipformer-transducer-model.h
Refactor online recognizer (#250)
2023-08-09 20:27:31 +08:00
onnx-utils.cc
Support streaming conformer CTC models from wenet (#427)
2023-11-16 10:35:23 +08:00
onnx-utils.h
Support streaming conformer CTC models from wenet (#427)
2023-11-16 10:35:23 +08:00
packed-sequence-test.cc
Add PackPaddedSequence (#85)
2023-03-08 14:12:20 +08:00
packed-sequence.cc
Add non-streaming ASR (#92)
2023-03-26 08:53:42 +08:00
packed-sequence.h
Add non-streaming ASR (#92)
2023-03-26 08:53:42 +08:00
pad-sequence-test.cc
add pad_sequence (#84)
2023-03-05 22:02:50 +08:00
pad-sequence.cc
add pad_sequence (#84)
2023-03-05 22:02:50 +08:00
pad-sequence.h
add pad_sequence (#84)
2023-03-05 22:02:50 +08:00
parse-options.cc
Test int8 models (#107)
2023-03-31 22:34:10 +08:00
parse-options.h
Added #include <cstdint> to fix gcc 13.2 compilation error. (#339)
2023-09-25 10:38:26 +08:00
piper-phonemize-lexicon.cc
Support VITS models from icefall. (#625)
2024-03-01 19:48:38 +08:00
piper-phonemize-lexicon.h
Use espeak-ng for coqui-ai/TTS VITS English models. (#466)
2023-12-06 11:00:38 +08:00
piper-phonemize-test.cc
Use piper-phonemize to convert text to token IDs (#453)
2023-11-30 23:57:43 +08:00
provider.cc
Support Android NNAPI. (#622)
2024-03-01 16:39:48 +08:00
provider.h
Support Android NNAPI. (#622)
2024-03-01 16:39:48 +08:00
README.md
Add Silero VAD (#313)
2023-09-17 14:54:38 +08:00
resample.cc
Add non-streaming ASR (#92)
2023-03-26 08:53:42 +08:00
resample.h
Support cross compiling for aarch64 (#52)
2023-02-21 22:04:21 +08:00
session.cc
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
session.h
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
sherpa-onnx-alsa-offline-audio-tagging.cc
Add C++ microphone examples for audio tagging (#749)
2024-04-10 21:00:35 +08:00
sherpa-onnx-alsa-offline-speaker-identification.cc
Refactor Java API (#806)
2024-04-24 18:41:48 +08:00
sherpa-onnx-alsa-offline.cc
Add C++ microphone examples for audio tagging (#749)
2024-04-10 21:00:35 +08:00
sherpa-onnx-alsa.cc
Fix the last character not being recognized for streaming paraformer models. (#799)
2024-04-22 15:10:39 +08:00
sherpa-onnx-keyword-spotter-alsa.cc
Add C++ microphone examples for audio tagging (#749)
2024-04-10 21:00:35 +08:00
sherpa-onnx-keyword-spotter-microphone.cc
Add C++ microphone examples for audio tagging (#749)
2024-04-10 21:00:35 +08:00
sherpa-onnx-keyword-spotter.cc
Refactor Java API (#806)
2024-04-24 18:41:48 +08:00
sherpa-onnx-microphone-offline-audio-tagging.cc
Add C++ microphone examples for audio tagging (#749)
2024-04-10 21:00:35 +08:00
sherpa-onnx-microphone-offline-speaker-identification.cc
Refactor Java API (#806)
2024-04-24 18:41:48 +08:00
sherpa-onnx-microphone-offline.cc
Add C++ microphone examples for audio tagging (#749)
2024-04-10 21:00:35 +08:00
sherpa-onnx-microphone.cc
Add function 'tolowerUnicode' in sherpa-onnx-microphone (fix #791) (#812)
2024-04-26 09:19:32 +08:00
sherpa-onnx-offline-audio-tagging.cc
Refactor Java API (#806)
2024-04-24 18:41:48 +08:00
sherpa-onnx-offline-language-identification.cc
Refactor Java API (#806)
2024-04-24 18:41:48 +08:00
sherpa-onnx-offline-parallel.cc
Refactor Java API (#806)
2024-04-24 18:41:48 +08:00
sherpa-onnx-offline-punctuation.cc
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
sherpa-onnx-offline-tts-play-alsa.cc
Add C API for speaker embedding extractor. (#711)
2024-03-28 18:05:40 +08:00
sherpa-onnx-offline-tts-play.cc
Add C API for speaker embedding extractor. (#711)
2024-03-28 18:05:40 +08:00
sherpa-onnx-offline-tts.cc
Add C API for speaker embedding extractor. (#711)
2024-03-28 18:05:40 +08:00
sherpa-onnx-offline.cc
Refactor Java API (#806)
2024-04-24 18:41:48 +08:00
sherpa-onnx-vad-alsa.cc
Add C++ microphone examples for audio tagging (#749)
2024-04-10 21:00:35 +08:00
sherpa-onnx-vad-microphone-offline-asr.cc
Add C++ microphone examples for audio tagging (#749)
2024-04-10 21:00:35 +08:00
sherpa-onnx-vad-microphone.cc
Add C++ microphone examples for audio tagging (#749)
2024-04-10 21:00:35 +08:00
sherpa-onnx.cc
Refactor Java API (#806)
2024-04-24 18:41:48 +08:00
silero-vad-model-config.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
silero-vad-model-config.h
Add Swift example for generating subtitles (#318)
2023-09-18 15:16:54 +08:00
silero-vad-model.cc
Add Android APK for Silero VAD (#335)
2023-09-23 20:39:13 +08:00
silero-vad-model.h
Add Android APK for Silero VAD (#335)
2023-09-23 20:39:13 +08:00
slice-test.cc
Add non-streaming ASR (#92)
2023-03-26 08:53:42 +08:00
slice.cc
Add non-streaming ASR (#92)
2023-03-26 08:53:42 +08:00
slice.h
Add non-streaming ASR (#92)
2023-03-26 08:53:42 +08:00
speaker-embedding-extractor-general-impl.h
Add Android demo for speaker recognition (#536)
2024-01-23 16:50:52 +08:00
speaker-embedding-extractor-impl.cc
Use a single thread when loading models (#703)
2024-03-26 13:35:33 +08:00
speaker-embedding-extractor-impl.h
Add Android demo for speaker recognition (#536)
2024-01-23 16:50:52 +08:00
speaker-embedding-extractor-model-meta-data.h
Add C++ runtime for models from 3d-speaker (#523)
2024-01-11 19:10:30 +08:00
speaker-embedding-extractor-model.cc
Add Android demo for speaker recognition (#536)
2024-01-23 16:50:52 +08:00
speaker-embedding-extractor-model.h
Add Android demo for speaker recognition (#536)
2024-01-23 16:50:52 +08:00
speaker-embedding-extractor-nemo-impl.h
Add Android demo for speaker recognition (#536)
2024-01-23 16:50:52 +08:00
speaker-embedding-extractor-nemo-model-meta-data.h
Add C++ runtime for speaker verification models from NeMo (#527)
2024-01-13 21:42:09 +08:00
speaker-embedding-extractor-nemo-model.cc
Add Android demo for speaker recognition (#536)
2024-01-23 16:50:52 +08:00
speaker-embedding-extractor-nemo-model.h
Add Android demo for speaker recognition (#536)
2024-01-23 16:50:52 +08:00
speaker-embedding-extractor.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
speaker-embedding-extractor.h
Add Android demo for speaker recognition (#536)
2024-01-23 16:50:52 +08:00
speaker-embedding-manager-test.cc
Add C++ runtime for speaker verification models from NeMo (#527)
2024-01-13 21:42:09 +08:00
speaker-embedding-manager.cc
Add score function to speaker identification (#775)
2024-04-16 17:29:46 +08:00
speaker-embedding-manager.h
Add score function to speaker identification (#775)
2024-04-16 17:29:46 +08:00
spoken-language-identification-impl.cc
Add Android demo for spoken language identification using Whisper multilingual models (#783)
2024-04-18 14:33:59 +08:00
spoken-language-identification-impl.h
Add Android demo for spoken language identification using Whisper multilingual models (#783)
2024-04-18 14:33:59 +08:00
spoken-language-identification-whisper-impl.h
Add Android demo for spoken language identification using Whisper multilingual models (#783)
2024-04-18 14:33:59 +08:00
spoken-language-identification.cc
Refactor TTS Android code to support jieba for Chinese TTS models (#800)
2024-04-22 17:21:05 +08:00
spoken-language-identification.h
Add Android demo for spoken language identification using Whisper multilingual models (#783)
2024-04-18 14:33:59 +08:00
stack-test.cc
Fix code style issues (#774)
2024-04-16 09:46:15 +08:00
stack.cc
Support CoreML for macOS (#151)
2023-05-12 15:57:44 +08:00
stack.h
Stack and streaming conformer support (#141)
2023-05-11 14:30:39 +08:00
symbol-table.cc
Support streaming zipformer CTC (#496)
2023-12-22 13:46:33 +08:00
symbol-table.h
Support whisper models (#238)
2023-08-07 12:34:18 +08:00
tee-stream.h
add streaming websocket server and client (#62)
2023-02-24 21:39:51 +08:00
text-utils.cc
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
text-utils.h
Support adding punctuations to the speech recogntion result (#761)
2024-04-13 12:15:57 +08:00
transducer-keyword-decoder.cc
Fix a bug in mean calculation of 'ys_probs' (#748)
2024-04-11 10:34:44 +08:00
transducer-keyword-decoder.h
decoder for open vocabulary keyword spotting (#505)
2024-01-20 22:52:41 +08:00
transpose-test.cc
Begin to support CTC models (#119)
2023-04-07 23:11:34 +08:00
transpose.cc
Begin to support CTC models (#119)
2023-04-07 23:11:34 +08:00
transpose.h
Begin to support CTC models (#119)
2023-04-07 23:11:34 +08:00
unbind-test.cc
Add Streaming zipformer (#50)
2023-02-21 20:00:03 +08:00
unbind.cc
Use deep copy in Clone() (#66)
2023-02-26 14:54:01 +08:00
unbind.h
Add Streaming zipformer (#50)
2023-02-21 20:00:03 +08:00
utfcpp-test.cc
Support Chinese vits models (#368)
2023-10-18 10:19:10 +08:00
utils.cc
decoder for open vocabulary keyword spotting (#505)
2024-01-20 22:52:41 +08:00
utils.h
decoder for open vocabulary keyword spotting (#505)
2024-01-20 22:52:41 +08:00
vad-model-config.cc
Add Silero VAD (#313)
2023-09-17 14:54:38 +08:00
vad-model-config.h
Add Silero VAD (#313)
2023-09-17 14:54:38 +08:00
vad-model.cc
Add Android APK for Silero VAD (#335)
2023-09-23 20:39:13 +08:00
vad-model.h
Add Android APK for Silero VAD (#335)
2023-09-23 20:39:13 +08:00
voice-activity-detector.cc
Add runtime support for wespeaker models (#516)
2024-01-09 22:06:08 +08:00
voice-activity-detector.h
Add runtime support for wespeaker models (#516)
2024-01-09 22:06:08 +08:00
wave-reader.cc
Add non-streaming ASR (#92)
2023-03-26 08:53:42 +08:00
wave-reader.h
Add non-streaming ASR (#92)
2023-03-26 08:53:42 +08:00
wave-writer.cc
Support writing generated audio samples to wave files (#363)
2023-10-13 23:36:03 +08:00
wave-writer.h
Support writing generated audio samples to wave files (#363)
2023-10-13 23:36:03 +08:00

README.md

File descriptions