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
f70fdd156c
Support using T-head-Semi/csi-nn2 for RISC-V ( #637 )
2024-03-06 18:21:50 +08:00
Fangjun Kuang
bdf9243940
Allow to not use pre-installed onnxruntime libs. ( #636 )
2024-03-06 14:40:23 +08:00
Fangjun Kuang
13260cdf49
Use self-compiled onnxruntime shared lib. ( #635 )
2024-03-06 11:03:24 +08:00
Fangjun Kuang
5dc2eaf2b4
Fix building wheels from source. ( #632 )
2024-03-04 16:39:51 +08:00
Fangjun Kuang
ed06ced16f
Add WebAssembly for NodeJS. ( #628 )
2024-03-03 20:00:36 +08:00
Fangjun Kuang
ac6825ff11
Refactor WebAssembly for nodejs ( #626 )
2024-03-02 12:31:36 +08:00
Fangjun Kuang
a65643b594
support onnxruntime v1.17.1 ( #624 )
2024-03-02 11:44:59 +08:00
Fangjun Kuang
d56964371c
Support VITS models from icefall. ( #625 )
2024-03-01 19:48:38 +08:00
dragon10
93836ff451
fixed variable's spell num_trailing_blanks ( #623 )
...
Signed-off-by: lonngxiang <lonngxiang@gmial.com >
Co-authored-by: lonngxiang <lonngxiang@gmial.com >
2024-03-01 17:02:10 +08:00
Fangjun Kuang
e2397cd1a4
Support Android NNAPI. ( #622 )
2024-03-01 16:39:48 +08:00
Fangjun Kuang
f9db33c926
Add WebAssembly demo for streaming trilingual Paraformer (Chinese+Cantonese+English) ( #618 )
2024-03-01 15:20:56 +08:00
Fangjun Kuang
c093880d7c
Fix building wheels ( #620 )
2024-03-01 15:20:06 +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
Fangjun Kuang
8b7928e7d6
Fix computing features for whisper. ( #617 )
2024-02-29 16:56:29 +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
85d59b5840
Use hub.nuaa.cf to replace huggingface URL to download dependencies. ( #614 )
2024-02-28 17:48:51 +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
fb04366179
Fix #608 ( #610 )
...
Fix java tests.
2024-02-26 13:49:37 +08:00
Fangjun Kuang
ee37d9bd92
Support RISC-V ( #609 )
2024-02-26 06:57:18 +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
a2df3535b7
Install wasm tts in a separate directory ( #600 )
2024-02-22 11:30:08 +08:00
Fangjun Kuang
7c22398dd8
Publish wasm tts to model scope. ( #599 )
2024-02-22 09:57:05 +08:00
Fangjun Kuang
7c4b59932a
Refactor WebAssembly build script. ( #598 )
...
Make it easier to build WebAssembly for ASR.
2024-02-21 16:51:15 +08:00
Fangjun Kuang
25079b5c05
Fix CI tests. ( #596 )
2024-02-21 15:37:27 +08:00
Fangjun Kuang
099a0ccae3
Link the math lib. ( #592 )
2024-02-21 15:36:54 +08:00
Fangjun Kuang
65eff9a6d1
Download ios-onnxruntime from github instead of huggingface. ( #593 )
2024-02-21 10:51:41 +08:00
Askars
763a51486e
Add missing start_time to python API ( #591 )
...
Co-authored-by: vsd-vector <askars.salimbajevs@tilde.lv >
2024-02-20 20:47:53 +08:00
Fangjun Kuang
12e5225401
Fix CI warnings ( #590 )
2024-02-20 15:28:47 +08:00
Fangjun Kuang
d2cc48ded5
Add more Chinese TTS models (Mandarin and Cantonese) ( #589 )
2024-02-20 15:05:35 +08:00
Fangjun Kuang
5f075d0fce
Support MinSizeRel and RelWithDebInfo build on Windows. ( #586 )
2024-02-20 10:22:02 +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
c68f39bd3c
Use onnxruntime static lib compiled with gcc8 on ubuntu 20.04 ( #587 )
2024-02-20 09:31:37 +08:00
Fangjun Kuang
2ab1fa022d
Download android onnxruntime libs from github. ( #584 )
...
It does not need to use git lfs any longer.
2024-02-19 10:32:58 +08:00
Paolo
92a8fd64f0
updated the icon on TTS engine for android ( #579 )
2024-02-19 10:25:01 +08:00
Fangjun Kuang
64007a6193
Support building debug version on Windows ( #583 )
2024-02-18 10:39:55 +08:00
Fangjun Kuang
81da0fb7a6
Update onnxruntime from 1.16.3 to 1.17.0 ( #581 )
2024-02-17 12:43:42 +08:00
Fangjun Kuang
d771762868
Support WebAssembly for text-to-speech ( #577 )
2024-02-08 23:39:12 +08:00
Fangjun Kuang
324a265523
Update README ( #572 )
2024-02-03 09:20:08 +08:00
ductranminh
665b869f03
Add context biasing for mobile ( #568 )
2024-02-01 21:33:22 +08:00
Fangjun Kuang
558f5e3263
Use sequential layout for OfflineTtsConfig in C# ( #567 )
2024-02-01 16:06:32 +08:00
Fangjun Kuang
2e8b321210
Add fine-tuned whisper model on aishell ( #565 )
...
See also https://github.com/k2-fsa/icefall/pull/1466
2024-01-31 17:23:42 +08:00
Fangjun Kuang
0b18ccfbb2
C++ API demo for speaker identification with portaudio. ( #561 )
2024-01-30 11:21:43 +08:00
20246688
0aa47e5ccc
Update test.py ( #560 )
2024-01-29 17:30:44 +08:00
Fangjun Kuang
be84932f86
Use curl to replace wget for Windows. ( #558 )
...
wget is not available on Windows in GitHub actions
2024-01-29 10:46:34 +08:00
Fangjun Kuang
fa2af5dc69
Add TTS demo for C# API ( #557 )
2024-01-28 23:29:39 +08:00
Fangjun Kuang
035a82df33
Add a new Persian tts model ( #555 )
2024-01-27 20:47:54 +08:00
Fangjun Kuang
44efff4e47
Fix CI tests for Python and JNI. ( #554 )
2024-01-27 13:01:54 +08:00
