louistiti
|
1d96655b01
|
fix(python tcp server): overflowed on ASR
|
2024-07-01 22:28:18 +08:00 |
|
louistiti
|
8eeff3a01c
|
feat(python tcp server): map speech synthesis hardware device choice to settings
|
2024-06-30 16:54:59 +08:00 |
|
louistiti
|
74241b43fe
|
feat(python tcp server): run speech synthesis inference on CPU
|
2024-06-30 16:30:12 +08:00 |
|
louistiti
|
1314217e00
|
BREAKING: upgrade from Python 3.9 to Python 3.11
|
2024-06-23 23:29:09 +08:00 |
|
louistiti
|
85c3a40457
|
chore(python tcp server): upgrade cx_Freeze to 7.1.1
|
2024-06-23 22:41:46 +08:00 |
|
louistiti
|
76b197baeb
|
refactor(python tcp server): ASR CUDA log notification on bootup
|
2024-06-22 21:03:27 +08:00 |
|
louistiti
|
3734a16b6a
|
fix(python tcp server): TTS inference correct params mapping
|
2024-06-21 09:51:52 +08:00 |
|
louistiti
|
8e28466cae
|
feat(python tcp server): improve TTS performance by using generator for inference
|
2024-06-21 09:38:53 +08:00 |
|
louistiti
|
a8ece30ced
|
fix(python tcp server): use CPU on macOS as a tmp fix against the memory leak for TTS
|
2024-06-20 22:24:25 +08:00 |
|
louistiti
|
963660db19
|
feat(python tcp server): empty cache on MPS PyTorch backend for TTS
|
2024-06-19 08:59:20 +08:00 |
|
louistiti
|
32dc3ced0b
|
feat: Apple Silicon support for voice models
|
2024-06-18 09:02:09 +08:00 |
|
louistiti
|
c9afb25ed3
|
feat(python tcp server): allow ASR device setting
|
2024-06-17 09:33:48 +08:00 |
|
louistiti
|
de3ceb76be
|
feat(python tcp server): unify settings to a single place, model settings included
|
2024-06-17 09:17:00 +08:00 |
|
louistiti
|
858b5090b4
|
feat(python tcp server): settings.json to store settings that can be edited on the fly
|
2024-06-16 23:33:47 +08:00 |
|
louistiti
|
ebe156e2d8
|
feat: new universal ASR logic for OS cross compatibility
|
2024-06-16 21:26:23 +08:00 |
|
louistiti
|
582b2aa572
|
feat: kick off ASR engine support for Apple Silicon
|
2024-06-12 00:31:47 +08:00 |
|
louistiti
|
7699739712
|
feat: add better quality TTS checkpoint
|
2024-06-08 02:17:26 +08:00 |
|
louistiti
|
7b8b702f92
|
fix(python tcp server): switch cx_Freeze to 7.1.0.post0 as 7.1.0 has been removed from the pip registry
|
2024-06-07 23:27:50 +08:00 |
|
louistiti
|
4ce470d3e7
|
feat(python tcp server): force TTS BERT local files
|
2024-06-06 08:43:06 +08:00 |
|
Louis Grenard
|
d3f3c4e3a7
|
feat(scripts): setup Python TCP server TTS language model files kick off
|
2024-06-05 23:39:59 +08:00 |
|
louistiti
|
11e8ad43ae
|
feat(python tcp server): use new V1_1 voice for TTS
|
2024-06-04 00:18:33 +08:00 |
|
louistiti
|
4cb374e64d
|
fix(python tcp server): exclude NVIDIA libs injection for non-macOS platforms on build
|
2024-06-02 00:10:25 +08:00 |
|
louistiti
|
fd76681f81
|
chore(python tcp server): upgrade cx_Freeze to 7.1.0 (may fix macOS wheel build)
|
2024-06-01 23:33:02 +08:00 |
|
louistiti
|
e250519c1b
|
feat: voice engine status sync with UI status
|
2024-05-29 23:39:44 +08:00 |
|
louistiti
|
0ce1f62c0d
|
feat: support default conversations powered by LLM with action-first in mind
|
2024-05-27 18:54:54 +08:00 |
|
louistiti
|
c18458ac41
|
feat(python tcp server): decrease throttling to 0.3s on ASR speech
|
2024-05-24 18:40:44 +08:00 |
|
louistiti
|
2fac3881eb
|
feat: support (very) long speech on ASR
|
2024-05-24 18:38:00 +08:00 |
|
louistiti
|
c1349c930a
|
feat: support incremental active listening for ASR
|
2024-05-24 01:26:28 +08:00 |
|
louistiti
|
91fb441dcd
|
feat: auto update mood on client; fix NER on slot filling
|
2024-05-23 17:49:55 +08:00 |
|
louistiti
|
9c8db3364b
|
chore: upgrade nodemon to 3.1.0 and minor improvements
|
2024-05-23 13:46:21 +08:00 |
|
louistiti
|
8a80f4fce6
|
feat(server): allow emojis with streamed answer and unify token clean up
|
2024-05-23 12:32:15 +08:00 |
|
louistiti
|
6b24e4280c
|
fix(python tcp server): correctly load .env variables
|
2024-05-23 09:43:03 +08:00 |
|
louistiti
|
beb208973f
|
feat(python tcp server): warm up TTS model on start
|
2024-05-23 09:24:46 +08:00 |
|
louistiti
|
0d370a8c7e
|
feat(python tcp server): fine tune parameters for the ASR
|
2024-05-22 20:52:01 +08:00 |
|
louistiti
|
7299f5fc4d
|
feat(python tcp server): add new wake word alternative
|
2024-05-22 18:58:22 +08:00 |
|
louistiti
|
8acdbec6e3
|
feat(python tcp server): increase voice speed on TTS engine
|
2024-05-22 18:56:11 +08:00 |
|
louistiti
|
e2bdbe9e8a
|
feat(python tcp server): add new wake word alternative
|
2024-05-22 17:57:07 +08:00 |
|
louistiti
|
c172f2d6af
|
fix(server): handle exception on NLU
|
2024-05-22 17:32:13 +08:00 |
|
louistiti
|
b02d510490
|
feat(server): always load ASR model from local
|
2024-05-22 15:22:30 +08:00 |
|
louistiti
|
596b7552dd
|
feat: new ASR engine ready
|
2024-05-21 23:57:36 +08:00 |
|
louistiti
|
f051c1d2cd
|
feat(python tcp server): ASR engine communication with core
|
2024-05-21 19:20:09 +08:00 |
|
louistiti
|
ef368f89fb
|
feat(python tcp server): multi threading and new ASR engine
|
2024-05-21 16:38:45 +08:00 |
|
louistiti
|
72390e2fe6
|
feat(python tcp server): update to latest TTS checkpoint
|
2024-05-20 09:06:03 +08:00 |
|
louistiti
|
39dae08b6b
|
feat(python tcp server): ASR PoC kick off
|
2024-05-20 00:29:39 +08:00 |
|
louistiti
|
e16782e2db
|
feat(server): add Leon mood info on init
|
2024-05-19 11:58:01 +08:00 |
|
louistiti
|
ed42f9b752
|
feat(python tcp server): prepare ASR entry point
|
2024-05-19 11:46:47 +08:00 |
|
louistiti
|
b25b82b9dc
|
feat(python tcp server): add break after : character on new TTS engine
|
2024-05-18 22:42:48 +08:00 |
|
louistiti
|
fd36eafb91
|
feat(python tcp server): increase socket content length
|
2024-05-18 22:42:12 +08:00 |
|
louistiti
|
a2e6466bb9
|
feat(python tcp server): clean up emojis on TTS engine
|
2024-05-18 22:20:15 +08:00 |
|
louistiti
|
f776913ca3
|
feat(server): complete first version of the new TTS engine
|
2024-05-18 21:45:46 +08:00 |
|