Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Spaces:
build-small-hackathon
/
thousand-token-theater
Running on Zero

App Files Files Community
Fetching metadata from the HF Docker repository...
thousand-token-theater
63.9 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 28 commits
HIMANSHUKUMARJHA's picture
HIMANSHUKUMARJHA
Fix skipped voice lines: one clip per beat (reads whole line) + cap beats to 2 sentences so the clip is short and fully read
6efb75e verified 23 days ago
  • .gitattributes
    1.52 kB
    initial commit 28 days ago
  • README.md
    7.38 kB
    Live text streaming + per-sentence autoplay voice (generate_stream + voice.synthesize; avoids the warm-up worker-reuse stall) 24 days ago
  • app.py
    28.9 kB
    Fix skipped voice lines: one clip per beat (reads whole line) + cap beats to 2 sentences so the clip is short and fully read 23 days ago
  • model.py
    4.02 kB
    Cleaner UI (strip duplicated speaker-name labels, no third-person self-naming) + faster (shorter one-sentence lines, max_new_tokens 140) 24 days ago
  • requirements.txt
    116 Bytes
    Add per-character VoxCPM2 voices; switch actors to MiniCPM5-1B; draining memory meter; save-highlights 24 days ago
  • test_engine.py
    3.16 kB
    Thousand-Token Theater: MiniCPM improv troupe with a hard 1,000-token memory 28 days ago
  • theater.py
    12.1 kB
    Fix skipped voice lines: one clip per beat (reads whole line) + cap beats to 2 sentences so the clip is short and fully read 23 days ago
  • voice.py
    6.72 kB
    Fix skipped voice lines: one clip per beat (reads whole line) + cap beats to 2 sentences so the clip is short and fully read 23 days ago