sxy
|
3a7a808de1
|
bugfix(tts): Fix polyphonic pronunciation bug
|
2022-09-22 20:28:11 +08:00 |
|
sxy
|
3ba163ea4e
|
model(tts): Update xiaoxin voice data
|
2022-09-21 11:35:19 +08:00 |
|
sxy
|
b578f17c23
|
voice_data: Update xiaoxin voice data
|
2022-09-15 14:36:40 +08:00 |
|
sxy
|
e1fd0f577b
|
feat(mfcc): accelerate MFCC lib
|
2022-09-08 20:25:17 +08:00 |
|
sxy
|
3c1617c051
|
doc: Update performance doc
|
2022-09-08 16:54:26 +08:00 |
|
sxy
|
08b9ffc864
|
bugfix: Fix ld error for macOS
|
2022-08-24 12:07:37 +08:00 |
|
sxy
|
8a40a5bcd1
|
Change src postion in CMakeList.txt
|
2022-08-23 19:25:07 +08:00 |
|
sxy
|
59024d2ae7
|
feat(mn): Add multinet5q8 Chinese model
|
2022-08-23 19:19:08 +08:00 |
|
sxy
|
15132edf68
|
feat(AFE): improve AEC in AFE_VC
|
2022-08-23 19:18:20 +08:00 |
|
sxy
|
218ca18372
|
feat(model): Update wn9_alexa(v3) to get better performence
|
2022-08-23 16:32:11 +08:00 |
|
sxy
|
4a87107f00
|
feat(tts): Support ESP-IDF v3.3 for esp32
|
2022-08-18 11:16:50 +08:00 |
|
sxy
|
cb59a9492d
|
bugfix: Add src/include path in component.mk
|
2022-08-17 20:57:55 +08:00 |
|
sxy
|
ea1ea85a49
|
feat(esp32): Support ESP-IDF v3.3 for esp32 chip
|
2022-08-17 20:29:21 +08:00 |
|
sxy
|
85349d2446
|
Fix warning in code
|
2022-08-17 20:23:13 +08:00 |
|
sxy
|
b562212fc6
|
doc(tts): Update TTS doc
|
2022-08-16 17:17:19 +08:00 |
|
sxy
|
20fb88366e
|
feat(tts): Remove redundant zero pronunciations
|
2022-08-16 16:58:02 +08:00 |
|
sxy
|
2e10bd44a0
|
feat(voice_set): Update xiaoxin voice set to support more external phrases
|
2022-08-16 16:55:07 +08:00 |
|
sxy
|
4a0a6763bf
|
docs: fix the invalid link in speech_command_recognition
|
2022-08-15 19:08:40 +08:00 |
|
sxy
|
6b21fdf970
|
feat(model): modify model loader to reduce model bin size for esp32
|
2022-08-15 15:03:18 +08:00 |
|
sxy
|
34e264eb5a
|
bugfix(wn): fix the bug can not switch wake word model for esp32
|
2022-08-12 21:10:01 +08:00 |
|
sxy
|
4936d92ea8
|
feat(tts): Add some extern phrase into xiaoxin voice data
|
2022-08-12 19:42:20 +08:00 |
|
sxy
|
98900ad8ef
|
bugfix(wn9_nihaoxiaozhi): Add wn9_nihaoxiaozhi path into movemodel.py
|
2022-08-11 11:30:29 +08:00 |
|
sxy
|
6047949d54
|
bugfix(tts): fix the bug in tts stretcher
|
2022-08-09 19:36:07 +08:00 |
|
sxy
|
39b6b85847
|
bugfix(afe): Add esp-dsp.a
|
2022-08-09 15:44:52 +08:00 |
|
sxy
|
759f7f8ecd
|
bugfix(wn): fix the bug in double swish activation
|
2022-08-09 15:37:17 +08:00 |
|
sxy
|
f3b627824b
|
doc: Update README
|
2022-08-02 14:19:55 +08:00 |
|
sxy
|
2086095c7c
|
feat(wn): Add nihaoxiaozhi wn9 and update alexa wn9 model
|
2022-08-02 10:31:53 +08:00 |
|
sxy
|
a9551636a1
|
feat(afe): add sample_rate in config to support 16KHz & 8KHz
|
2022-08-02 10:31:12 +08:00 |
|
sxy
|
ca91b72284
|
feat(tts): Update esp32 TTS lib
|
2022-07-27 21:10:37 +08:00 |
|
sxy
|
1412145066
|
feat(tts): Updata TTS and xiaoxin voice data
|
2022-07-27 20:20:52 +08:00 |
|
sxy
|
bbbe7849cd
|
refact: rename AFE handle for voice communication
|
2022-07-20 19:53:19 +08:00 |
|
sxy
|
af859c9012
|
feat(esp32): Update ESP32 lib and APIs
|
2022-07-20 15:59:54 +08:00 |
|
sxy
|
a6074009a2
|
feat(esp-tts): Add xiaoxin voice data and update xiaole voice data
|
2022-07-20 15:23:21 +08:00 |
|
sxy
|
4b0be3139c
|
feat(tts): Update tts lib for esp32,esp32s2,esp32s3
|
2022-07-20 15:23:06 +08:00 |
|
sxy
|
08add1d4f6
|
feat(tts): update esp-chinese-tts v1.3
|
2022-07-18 19:37:46 +08:00 |
|
sxy
|
05d2dbfd9e
|
doc(mn): Fix the error link in speech_commands_recognition/README
|
2022-07-15 10:47:55 +08:00 |
|
sxy
|
16f62a4b81
|
doc(wn): Add a table to show the model for different SoCs
|
2022-07-15 10:40:04 +08:00 |
|
sxy
|
555571a5a9
|
doc(wn): Fix the error link in wake_word_engine/README
|
2022-07-15 10:25:58 +08:00 |
|
sxy
|
a127d88913
|
feat(wn): fix the threshold of alexa
|
2022-07-12 17:25:39 +08:00 |
|
sxy
|
42e30deb34
|
doc(afe): Update AFE v2.0 API document
|
2022-07-12 14:35:21 +08:00 |
|
sxy
|
e86a914a02
|
refactor: delect unused files
|
2022-07-08 20:21:59 +08:00 |
|
sxy
|
ac47452d21
|
feat: Update API for release v2.0
|
2022-07-08 19:25:49 +08:00 |
|
sxy
|
f76da537fd
|
feat(wn): Add wakenet9 models
|
2022-07-08 19:25:25 +08:00 |
|
sxy
|
728335198d
|
doc: Update flash_model,wakenet,multinet doc
|
2022-07-08 16:19:22 +08:00 |
|
Wang Wang Wang
|
09f3e84d92
|
Merge branch 'doc_review' into 'dev/2.0'
doc: Update docs
See merge request speech-recognition-framework/esp-sr!1
|
2022-03-08 14:51:42 +08:00 |
|
Wang Wang Wang
|
1841f9151c
|
doc: Update docs
|
2022-03-08 14:47:58 +08:00 |
|
Wang Wang Wang
|
71e8f3e1e5
|
feat(AFE): Add MISO V2
|
2022-02-25 20:22:26 +08:00 |
|
Wang Wang Wang
|
f4f7b7f9bd
|
bugfix(WN): Fix the bug of Hilexin7q8
|
2022-02-21 16:52:17 +08:00 |
|
Wang Wang Wang
|
c873a359e7
|
feat(MN): Fix the memory leak of MN; Modify the method of resetting speech commands
|
2022-02-17 14:23:09 +08:00 |
|
Wang Wang Wang
|
66a12ee570
|
bugfix(AFE): clean up the warnings and errors
|
2022-02-10 21:17:26 +08:00 |
|