Spaces:

Remsky
/

Kokoro-TTS-Zero

Running on Zero

App Files Files Community

Kokoro-TTS-Zero

1 contributor

History: 53 commits

Remsky

Enhance processing metrics in TTSModelV1 by calculating total audio duration and processing time per chunk

a010fd1 15 days ago

lib
Update lib/ui_content.py about 1 month ago
samples
Delete samples/af_nicole_bf_isabella_af_bella.wav about 1 month ago
texts
Add .gitignore, update requirements, and implement book processing utilities about 1 month ago
voices
Refactor TTSModelV1 to remove JSON voice mappings and load voices from the voices_v1 directory 15 days ago
voices_v1
Refactor TTSModelV1 to remove JSON voice mappings and load voices from the voices_v1 directory 15 days ago
.gitattributes

1.56 kB

Add wav files and GPU timeout changes about 1 month ago
.gitignore

146 Bytes

Update TTSModel to verify local voice files and handle missing downloads 15 days ago
README.md

1.12 kB

Add v1.0.0 model support with KPipeline implementation 15 days ago
app.py

20.4 kB

Add animated version announcement for V1.0.0 in the demo interface 15 days ago
packages.txt

10 Bytes

Add initial implementation of Kokoro TTS Demo Space with Gradio interface and dependencies about 1 month ago
parse_chapters.py

1.01 kB

Add .gitignore, update requirements, and implement book processing utilities about 1 month ago
requirements.txt

249 Bytes

Update requirements.txt 15 days ago
the_time_machine_hgwells.txt

180 kB

Added Multi-Voice, GPU Timeout, etc about 1 month ago
tts_factory.py

650 Bytes

Update model version to v1.0.0 and adjust initialization logic for voice selection 15 days ago
tts_model.py

13.2 kB

Update TTSModel to verify local voice files and handle missing downloads 15 days ago
tts_model_v1.py

6.7 kB

Enhance processing metrics in TTSModelV1 by calculating total audio duration and processing time per chunk 15 days ago