8.39 GB

Ctrl+K

1 contributor

History: 10 commits

penguinfish1688

Record successful public inference with custom audio references

f063927 verified about 3 hours ago

dude_tts
Support user-provided speaker audio with a bundled reference encoder about 3 hours ago
examples
Present DuDE as full-duplex conversation TTS with named samples and verified held-out provenance about 4 hours ago
speaker_encoder
Support user-provided speaker audio with a bundled reference encoder about 3 hours ago
speech_tokenizer
Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago
voices
Present DuDE as full-duplex conversation TTS with named samples and verified held-out provenance about 4 hours ago
.gitattributes

2.02 kB
Present DuDE as full-duplex conversation TTS with named samples and verified held-out provenance about 4 hours ago
CITATION.cff

304 Bytes
Support user-provided speaker audio with a bundled reference encoder about 3 hours ago
LICENSE

204 Bytes
Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago
LICENSE-CODE

11.3 kB
Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago
LICENSE-QWEN

11.3 kB
Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago
README.md

9.08 kB
Support user-provided speaker audio with a bundled reference encoder about 3 hours ago
config.json

4.91 kB
Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago
event-token-map.json

134 Bytes
Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago
generation_config.json

245 Bytes
Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago
infer.py

1.25 kB
Support user-provided speaker audio with a bundled reference encoder about 3 hours ago
merges.txt

1.67 MB
Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago
model.safetensors

7.67 GB
xet

Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago
preprocessor_config.json

127 Bytes
Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago
provenance.json

2.75 kB
Present DuDE as full-duplex conversation TTS with named samples and verified held-out provenance about 4 hours ago
release.json

1.48 kB
Support user-provided speaker audio with a bundled reference encoder about 3 hours ago
requirements.txt

249 Bytes
Support user-provided speaker audio with a bundled reference encoder about 3 hours ago
tokenizer_config.json

7.34 kB
Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago
verification.json

1.52 kB
Record successful public inference with custom audio references about 3 hours ago
vocab.json

2.78 MB
Release standalone duplex TTS with XML interleaver, voice presets and examples about 4 hours ago