umbragit/Qwen3-TTS
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Commit Graph

  • 012e45298d Add UmbraAudio Voice Studio branding to web demo (icon + favicon) main B.D. Murphy 2026-09-22 19:12:21 -07:00
  • 022e286b98 fix finetuning bug Xiong Wang 2026-03-17 14:38:41 +08:00
  • 6cafe5582c fix: padding value process bug in tokenizer decode Xiong Wang 2026-02-06 12:11:31 +08:00
  • 5f8581d05e fix: padding bugs in 12Hz tokenizer decode. Xiong Wang 2026-02-05 14:32:14 +08:00
  • 680d4e9d0e fix: adjust finetune script for stable training. Xiong Wang 2026-02-04 11:15:24 +08:00
  • 1ab0dd7535 update: update readme Xiong Wang 2026-01-26 00:11:02 +08:00
  • 3b30a4e509 update: update readme Xiong Wang 2026-01-24 21:44:35 +08:00
  • c25ce958ea Merge pull request #15 from vasqu/fix-fa-flags Xiong Wang 2026-01-24 16:32:32 +08:00
  • ab0f77849b fix loading logic vasqu 2026-01-23 10:48:11 +01:00
  • 587ebf6389 fixup wrong flags vasqu 2026-01-23 10:18:08 +01:00
  • 0c6a7cbb6c update: modify default non_streaming_mode Xiong Wang 2026-01-23 14:08:26 +08:00
  • 8a98526da0 fix and update: fix finetuning/prepare_data.py and update citation Xiong Wang 2026-01-23 13:19:19 +08:00
  • d5c446171a fix: hf speech_tokenizer download bug. Xiong Wang 2026-01-22 23:34:21 +08:00
  • d8146d5305 Initial commit Xiong Wang 2026-01-22 17:57:04 +08:00