Fetching metadata from the HF Docker repository...
Feb 28, 2025 11:31 Update WebUI title to indicate unofficial status Running - Modify HTML title in webui.py
- Add "(Unofficial)" prefix to Spark-TTS title
- Improve transparency about project's status 11:29 Add GPU initialization logging in generate function - Add print statement to log GPU model transfer
- Provide visibility into GPU device handling
- Maintain existing GPU transfer logic 11:23 Optimize GPU device handling in generate function - Simplify model device transfer method
- Remove redundant `.to("cuda")` assignment
- Ensure model is correctly moved to GPU when available 11:22 Refactor model initialization and GPU handling in generate function - Simplify model initialization logic
- Ensure model is initialized with correct device
- Remove redundant GPU logging
- Improve device selection for model loading 11:16 Improve model initialization and GPU handling in webui.py - Add error handling for uninitialized model
- Ensure model is only initialized once
- Add GPU initialization logging
- Prevent redundant model loading 10:43 Add device method to BiCodecTokenizer 10:30 All model to have device changed 10:26 test with global model 10:19 Move EfficientAttentionConfig to module level 10:16 replace the namedtupple for an object to avoid pickling issues 09:26 typo gpu -> GPU 09:23 Test zero gpu 09:15 default to cpu for testing 09:11 download model from HF 08:54 update color 08:51 update yaml 07:50 update readme with yaml 06:08 add windows install guide spark-tts
06:06 add windows install guide spark-tts
05:39 fix webui OOM bug spark-tts
05:10 Merge branch 'main' of github.com:SparkAudio/Spark-TTS spark-tts
05:09 update overview fig spark-tts
Feb 27, 2025 10:57 Merge pull request #2 from pandamq/main Xinsheng Wang
Update webui.py 10:26 Update webui.py Mingqi Jiang
09:51 release spark-tts
06:36 support voice creation shell script 05:32 update readme spark-tts
05:29 Merge branch 'main' of github.com:SparkAudio/Spark-TTS spark-tts
05:28 update readme spark-tts
04:21 modify audio tokenizer example Feb 26, 2025 12:45 update readme spark-tts
12:40 Update README spark-tts
12:33 Update README spark-tts
12:31 add webui spark-tts
12:27 Merge branch 'main' of github.com:SparkAudio/Spark-TTS spark-tts
12:24 add webui spark-tts
12:22 support voice creation spark-tts
07:51 Update README.md Mingqi J
Update Demo table 07:10 Update README.md Mingqi J
update demo for webm 03:35 update demo 02:39 add demo spark-tts
Feb 25, 2025 13:54 test webm spark-tts
06:15 clean structure spark-tts
05:36 add demo spark-tts
05:27 update demo spark-tts
05:23 add demos spark-tts
03:46 udpate logo spark-tts
03:45 add readme spark-tts
02:15 init spark-tts
01:29 Initial commit Xinsheng Wang
