74c41a3e44
Add text normalization for Chinese, Japanese, and English
...
Implement regex-based text normalization functionality to support trilingual (CJE) content processing
2025-05-16 11:10:58 +08:00
6a96f35eae
Merge pull request #1 from yuyun2000/opt/melotts
...
Refactor SOLA component code
2025-05-15 15:24:45 +08:00
ebf908a0d1
Merge branch 'dev' into opt/melotts
2025-05-15 15:24:36 +08:00
10e4bdf828
Refactor SOLA component code
...
Streamline and simplify code in the SOLA module for improved readability and maintenance
2025-05-15 15:17:04 +08:00
7d392a3c74
Merge branch 'dev' of github.com:m5stack/StackFlow into dev
2025-05-12 10:21:13 +08:00
87744d2abc
[update] README.md add model list
2025-05-12 10:20:54 +08:00
6e503a130c
[update] delete debug log
2025-05-09 18:42:20 +08:00
e5944f242d
Merge pull request #14 from yuyun2000/opt/melotts
...
Fix SOLA algorithm implementation
2025-05-09 18:28:15 +08:00
835daf192c
Fix SOLA algorithm implementation
...
Resolved issues in the Synchronized Overlap-Add (SOLA) algorithm to ensure proper audio processing and alignment.
2025-05-09 18:25:49 +08:00
3b20852f1e
Merge pull request #13 from yuyun2000/opt/melotts
...
Opt/melotts
2025-05-09 17:50:47 +08:00
9e7342f3b1
Fix code formatting and integrate SOLA algorithm into main.py
...
Corrected code formatting issues and moved the SOLA (Synchronized Overlap-Add) algorithm implementation into main.py for better code organization.
2025-05-09 17:43:17 +08:00
74603beede
[update] update qwen3-0.6B model
2025-05-09 17:36:19 +08:00
cbb0afaf65
Optimize G2P process to skip inference for short audio clips
...
Improved the Grapheme-to-Phoneme (G2P) process by eliminating separate inference operations for audio segments that are too short, enhancing processing efficiency.
2025-05-09 17:24:57 +08:00
b1df925af9
Fix SOLA detail issue causing first frame problems
...
Resolved an issue in the SOLA (Synchronized Overlap-Add) implementation where specific details were causing problems with the first frame of audio processing.
2025-05-09 17:01:55 +08:00
b43e73e949
[add] add benchmark.yml
2025-05-08 17:19:33 +08:00
6b285ed98d
[update] update benchmark
2025-05-08 17:15:50 +08:00
40bfe39c85
[update] update whisper-small
2025-05-07 10:07:36 +08:00
e1d7e6d15f
Merge pull request #12 from yuyun2000/opt/melotts
...
Make MeloTTS logs English & add G2P debug toggle and SOLA algorithm
2025-05-06 18:35:19 +08:00
840f739c70
[update] update whisper-base
2025-05-06 17:18:39 +08:00
a151affa1d
Translate logs in Lexicon.hpp to English and add debug switch
...
- Convert all Chinese log messages in Lexicon.hpp to English for better international compatibility\n- Add a debug flag to control whether to display g2p process logs\n- Improve code readability and debugging experience
2025-05-06 16:50:35 +08:00
e3c70bc127
Implement Sola algorithm for smoother audio transitions
...
Apply the Synchronized Overlap-Add (SOLA) algorithm to smooth the connection between audio segments output by the decoder, resulting in more natural-sounding transitions between segments.
2025-05-06 16:48:11 +08:00
2a8a744777
[update] StackFlow add stackflow_data && pzmq add get_param set_param
2025-05-06 15:25:54 +08:00
4e301f1cbf
[update] update whisper-tiny
2025-05-06 11:11:31 +08:00
1e85f45413
[update] update llm-model-melotts-en-default & llm-model-melotts-ja-jp
2025-04-30 19:40:58 +08:00
04961aea99
[update] update mode_melotts-en-default.json
2025-04-30 17:37:04 +08:00
yuyun2000
Xuanwu Yun
dianjixz
LittleMouse
Abandon-ht