tech08mag/qwen3-tts-testing
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

qwen example and futher documantation

Browse Source
This commit is contained in:
Tech08mag
2026-07-26 14:39:45 +02:00
parent 74fc6dc31c
commit 1428e150ce
7 changed files with 77 additions and 446 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+16 -2
View File
@@ -5,6 +5,10 @@ RAM: 16GB DDR5 4800 MTS (may be used for loading the model)\
SWAP: 8 GB (not used)\
Modell: https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice
flash-attn wasn't used
Installation modification:
Uninstalled all cuda related deependencies and installed for all pytorch related packages the rocm version
Example - Cpu \
Generation time: 657.36s\
@@ -13,7 +17,7 @@ Real-time factor: 7.42x\
text: cpu\
Speaker: Ryan\
Language: English\
Instruct: read the text in a calm and soothing voice, with a slight emphasis on key points, and maintain a steady pace throughout the narration.\
Instruct: read the text in a calm and soothing voice, with a slight emphasis on key points, and maintain a steady pace throughout the narration.
Example - Raid\
Generation time: 2315.90s\
@@ -33,6 +37,14 @@ Speaker: Aiden\
Language: English\
Instruct: read the text in a calm and soothing voice, with a slight emphasis on key points, and maintain a steady pace throughout the narration.
Example - [Qwen](https://dev.to/czmilo/qwen3-tts-the-complete-2026-guide-to-open-source-voice-cloning-and-ai-speech-generation-1in6)
Generation time: 386.22s
Audio duration: 52.88s
Real-time factor: 7.30x
Speaker: Aiden\
Language: qwen\
Instruct: read the text in a calm and soothing voice, with a slight emphasis on key points, and maintain a steady pace throughout the narration.
Example - [Offener Brief: Microsoft, Nvidia & Co. fordern offenes KI-Ökosystem](https://www.heise.de/news/Offener-Brief-Microsoft-Nvidia-Co-fordern-offenes-KI-Oekosystem-11378076.html)\
(offically not supported)\
Generation time: 903.47s\
@@ -42,4 +54,6 @@ Speaker: Aiden\
Language: German\
Instruct: read the text in a calm and soothing voice, with a slight emphasis on key points, and maintain a steady pace throughout the narration.
VRAM Usage is most of the time below 4GB.
VRAM Usage is most of the time below 4GB.
Notice the modell loading needs some time so I assume that the warmup time explain the fluctuating results between the real time factors