Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

Spaces:
nexusbert
/
tts_new
Sleeping

App Files Files Community
Fetching metadata from the HF Docker repository...
tts_new
249 kB
  • 1 contributor
History: 39 commits
nexusbert's picture
nexusbert
Add voice chat feature with audio storage
4d777b5 9 days ago
  • yarngpt
    Sync: add API, Dockerfile, assets (no large ckpt) about 2 months ago
  • .gitattributes
    1.52 kB
    initial commit 2 months ago
  • .gitignore
    146 Bytes
    Sync: add API, Dockerfile, assets (no large ckpt) about 2 months ago
  • Dockerfile
    2.04 kB
    Install ffmpeg for torchcodec runtime support about 2 months ago
  • README.md
    91 Bytes
    push 2 months ago
  • app.py
    197 Bytes
    Simplify audio post-processing; set pad token; add generation logging about 2 months ago
  • main.py
    28.3 kB
    Add voice chat feature with audio storage 9 days ago
  • requirements.txt
    201 Bytes
    ASR+Ask integration, single /speak, scipy WAV, build-time ASR cache, cleanup about 2 months ago
  • wavtokenizer_mediumdata_frame75_3s_nq1_code4096_dim512_kmeans200_attn.yaml
    2.79 kB
    Sync: add API, Dockerfile, assets (no large ckpt) about 2 months ago