Package: pocket-tts Version: 4.0.1+git20261121.56b2e69-1+5.1 Architecture: all Maintainer: Danny Milosavljevic Installed-Size: 354 Depends: python3:any, python3 (>= 3.10), python3 (<< 3.15), python3-einops (>= 0.4.0), python3-fastapi (>= 0.100), python3-huggingface-hub (>= 0.13.0), python3-numpy (>= 2), python3-pydantic (>= 2), python3-python-multipart (>= 0.0.21), python3-requests (>= 2.20.0), python3-safetensors (>= 0.4.0), python3-scipy (>= 1.5.0), python3-sentencepiece (>= 0.2.1), python3-tokenizers (>= 0.21), python3-torch (>= 2.5.0), python3-typer (>= 0.10.0), python3-typing-extensions (>= 4.10.0), python3-uvicorn (>= 0.13.0), python3-yaml (>= 6.0) Suggests: speech-dispatcher (>= 0.12), python3-soundfile (>= 0.12.0) Filename: all/pocket-tts_4.0.1+git20261121.56b2e69-1+5.1_all.deb Size: 67264 MD5sum: 4f0bda715f55b13f04657b3a19ccd5dc SHA1: ab7ac1426a4020e1e6e7143fbdc68bba14c1f477 SHA256: 39078b541066ed235d43546f39158c6ce9084fec4b13eeae6324d1ecce48d5f3 Section: sound Priority: optional Homepage: https://github.com/friendly-machines-com/pocket-tts/tree/speech-dispatcher Description: CPU text-to-speech with a Speech Dispatcher output module Pocket TTS is Kyutai's compact, CPU-based speech synthesis engine. This snapshot includes the pocket-tts CLI and Python API, and sd-pocket-tts for use with Speech Dispatcher. Model files are fetched on first use. Package: python3-einops Source: python-einops Version: 0.8.2-1 Architecture: all Maintainer: Debian Deep Learning Team Installed-Size: 259 Depends: python3:any Recommends: python3-numpy Suggests: python3-torch | python3-torch-cuda | python3-torch-rocm, python3-cupy | python3-cupy-rocm, python3-jax | python3-jax-cuda Filename: all/python3-einops_0.8.2-1_all.deb Size: 48640 MD5sum: 0c3fde2c03cc6ae60b02a90d6c72b5bc SHA1: 81309b22b2aa3b1d181e18f722a79573650e9a70 SHA256: d564d6c75cf62df97441decac0f204a5f005148a8e150f1e1649f3370fe61191 Section: science Priority: optional Homepage: https://github.com/arogozhnikov/einops Description: Flexible and powerful tensor operations for readable code einops stands for Einstein-Inspired Notation for operations (though "Einstein operations" is more attractive and easier to remember). Notation was loosely inspired by Einstein summation (in particular by numpy.einsum operation). . Supports numpy, pytorch, tensorflow, jax, and others.