Fangjun Kuang
2e0bccad36
Add C API for speaker embedding extractor. ( #711 )
2024-03-28 18:05:40 +08:00
Leo Huang
638f48f47a
Added progress for callback of tts generator ( #712 )
...
Co-authored-by: leohwang <leohwang@360converter.com >
2024-03-28 17:12:20 +08:00
Fangjun Kuang
a042f44076
Add Golang API for spoken language identification. ( #709 )
2024-03-27 19:40:25 +08:00
Fangjun Kuang
4e040c596e
Support including TTS conditionally. ( #699 )
2024-03-26 17:21:35 +08:00
Fangjun Kuang
d364610605
Use a single thread when loading models ( #703 )
2024-03-26 13:35:33 +08:00
Fangjun Kuang
0d258dd150
Support spoken language identification with whisper ( #694 )
2024-03-24 22:57:00 +08:00
Fangjun Kuang
1952772654
Add timestamps and tokens for .Net's online models. ( #690 )
2024-03-23 18:51:56 +08:00
Karel Vesely
eaec4c83c2
Configurable low_freq high_freq, dithering ( #664 )
2024-03-22 21:41:44 +08:00
Fangjun Kuang
c8770aec20
Add nuget package for Windows x86 ( #683 )
2024-03-21 14:57:01 +08:00
Fangjun Kuang
acf0975153
Support whisper language/task in various language bindings. ( #679 )
2024-03-20 16:43:35 +08:00
Lovemefan
009ed2cd30
add WebAssembly for Kws ( #648 )
2024-03-11 21:02:31 +08:00
Fangjun Kuang
d3287f9494
Add Python ASR examples with alsa ( #646 )
2024-03-08 11:34:48 +08:00
Wei Kang
e9e8d755d9
Fix detetion at the tail when using hotwords in streaming model ( #638 )
2024-03-08 10:04:33 +08:00
Fangjun Kuang
bdf9243940
Allow to not use pre-installed onnxruntime libs. ( #636 )
2024-03-06 14:40:23 +08:00
Fangjun Kuang
d56964371c
Support VITS models from icefall. ( #625 )
2024-03-01 19:48:38 +08:00
Fangjun Kuang
e2397cd1a4
Support Android NNAPI. ( #622 )
2024-03-01 16:39:48 +08:00
Wei Kang
734bbd91dc
Add Python API for keyword spotting ( #576 )
...
* Add alsa & microphone support for keyword spotting
* Add python wrapper
2024-03-01 09:31:11 +08:00
Karel Vesely
38c072dcb2
Track token scores ( #571 )
...
* add export of per-token scores (ys, lm, context)
- for best path of the modified-beam-search decoding of transducer
* refactoring JSON export of OnlineRecognitionResult, extending pybind11 API of OnlineRecognitionResult
* export per-token scores also for greedy-search (online-transducer)
- export un-scaled lm_probs (modified-beam search, online-transducer)
- polishing
* fill lm_probs/context_scores only if LM/ContextGraph is present (make Result smaller)
2024-02-29 06:28:45 +08:00
Fangjun Kuang
0cb6d1b474
support using xnnpack as execution provider ( #612 )
2024-02-28 17:32:48 +08:00
Fangjun Kuang
87a7030c08
Support using alsa to access the microphone with non-streaming ASR models ( #517 )
2024-02-26 21:17:26 +08:00
Fangjun Kuang
67acd34dcd
Use alsa to read microphone in speaker identification demo. ( #605 )
2024-02-23 19:27:51 +08:00
Fangjun Kuang
16ba7e274a
Add WebAssembly for ASR ( #604 )
2024-02-23 17:39:11 +08:00
Fangjun Kuang
099a0ccae3
Link the math lib. ( #592 )
2024-02-21 15:36:54 +08:00
Fangjun Kuang
3d2c7fad74
Increase the right chunk size of streaming paraformer to 3 ( #588 )
2024-02-20 09:44:40 +08:00
Fangjun Kuang
d771762868
Support WebAssembly for text-to-speech ( #577 )
2024-02-08 23:39:12 +08:00
Fangjun Kuang
0b18ccfbb2
C++ API demo for speaker identification with portaudio. ( #561 )
2024-01-30 11:21:43 +08:00
Fangjun Kuang
fa2af5dc69
Add TTS demo for C# API ( #557 )
2024-01-28 23:29:39 +08:00
Karel Vesely
3f2a17ef47
Fixes issue #535 , fix hexa 1-char tokens in ASR output. ( #550 )
...
- Avoid output like : `[' K', '<0x64>', '<0x79>', 'ť', ' a', '<0x75>',
'to', 'bu', '<0x73>', '<0x75>', ... ]` with regular 500 BPE units.
- Don't rewrite 1-char tokens in range [ 0x20 (space) .. 0x7E (tilde) ]
2024-01-26 19:23:20 +08:00
chiiyeh
e7b18a2139
add blank_penalty for online transducer ( #548 )
2024-01-26 12:12:13 +08:00
chiiyeh
3bb3849ec5
add blank_penalty for offline transducer ( #542 )
2024-01-25 15:00:09 +08:00
Fangjun Kuang
bbd7c7fc18
Add Android demo for speaker recognition ( #536 )
...
See pre-built Android APKs at
https://k2-fsa.github.io/sherpa/onnx/speaker-identification/apk.html
2024-01-23 16:50:52 +08:00
Wei Kang
b6c020901a
decoder for open vocabulary keyword spotting ( #505 )
...
* various fixes to ContextGraph to support open vocabulary keywords decoder
* Add keyword spotter runtime
* Add binary
* First version works
* Minor fixes
* update text2token
* default values
* Add jni for kws
* add kws android project
* Minor fixes
* Remove unused interface
* Minor fixes
* Add workflow
* handle extra info in texts
* Minor fixes
* Add more comments
* Fix ci
* fix cpp style
* Add input box in android demo so that users can specify their keywords
* Fix cpp style
* Fix comments
* Minor fixes
* Minor fixes
* minor fixes
* Minor fixes
* Minor fixes
* Add CI
* Fix code style
* cpplint
* Fix comments
* Fix error
2024-01-20 22:52:41 +08:00
Fangjun Kuang
2024e96639
Add C++ runtime for speaker verification models from NeMo ( #527 )
2024-01-13 21:42:09 +08:00
Fangjun Kuang
afc81ec122
Add C++ runtime for models from 3d-speaker ( #523 )
2024-01-11 19:10:30 +08:00
Fangjun Kuang
07e2b9a36d
Support exporting models to onnx from 3D-Speaker ( #522 )
2024-01-10 21:09:45 +08:00
Fangjun Kuang
55266918c8
Add runtime support for wespeaker models ( #516 )
2024-01-09 22:06:08 +08:00
Fangjun Kuang
0be71a31f5
Use high_freq -400 in computing fbank features. ( #515 )
...
Fixes #514
2024-01-04 12:39:06 +08:00
Fangjun Kuang
e215d0c39a
Fix Byte BPE string results for Python. ( #512 )
...
It ignores invalid UTF8 strings.
2024-01-03 16:03:24 +08:00
Fangjun Kuang
d7e10bb3f8
Replace Android system TTS engine ( #508 )
2023-12-31 23:02:35 +08:00
Fangjun Kuang
e475e750ac
Support streaming zipformer CTC ( #496 )
...
* Support streaming zipformer CTC
* test online zipformer2 CTC
* Update doc of sherpa-onnx.cc
* Add Python APIs for streaming zipformer2 ctc
* Add Python API examples for streaming zipformer2 ctc
* Swift API for streaming zipformer2 CTC
* NodeJS API for streaming zipformer2 CTC
* Kotlin API for streaming zipformer2 CTC
* Golang API for streaming zipformer2 CTC
* C# API for streaming zipformer2 CTC
* Release v1.9.6
2023-12-22 13:46:33 +08:00
Fangjun Kuang
03ff9db56e
Keep multiple threads from calling into espeak-ng at the same time ( #489 )
2023-12-15 17:44:33 +08:00
Fangjun Kuang
ad72e7afc3
Print informative error messages for sherpa-onnx-alsa on errors. ( #486 )
2023-12-15 11:10:39 +08:00
Fangjun Kuang
b18812ceff
Play generated audio using alsa for TTS ( #482 )
2023-12-13 22:28:03 +08:00
Fangjun Kuang
0e23f82691
Give an informative log for whisper on exceptions. ( #473 )
2023-12-08 14:33:59 +08:00
Fangjun Kuang
868c339e5e
Support distil-small.en whisper ( #472 )
2023-12-08 11:59:20 +08:00
Fangjun Kuang
3ae984f148
Remove the 30-second constraint from whisper. ( #471 )
2023-12-07 17:47:08 +08:00
Fangjun Kuang
d34161413d
Support Ukrainian VITS models from coqui-ai/TTS ( #469 )
2023-12-06 19:37:11 +08:00
Fangjun Kuang
23cf92daf7
Use espeak-ng for coqui-ai/TTS VITS English models. ( #466 )
2023-12-06 11:00:38 +08:00
Fangjun Kuang
86b4be5260
Break text into sentences for tts. ( #460 )
...
This is for models that are not using piper-phonemize as their front-end.
2023-12-03 11:50:25 +08:00
Fangjun Kuang
99ff6a834c
Play generated audio as it is generating. ( #457 )
2023-12-02 15:35:11 +08:00
