Metadata-Version: 2.1
Name: haaztest-kitten-inference-tts2-rocm
Version: 0.2.0
Summary: Kitten TTS 2 native engine for AMD Radeon GPUs (ROCm), used by kitten-inference-tts2
Home-page: https://github.com/KittenML/kitten-inference
License: Apache-2.0 for KittenML's code. The library also contains third-party code under other licenses (LGPL-2.1-or-later, BSD-3-Clause, MIT, NCSA and more, including AMD ROCm code), listed in kitten_inference/_tts2_rocm/licenses/NOTICE; the whole is not Apache-2.0-only
Classifier: Operating System :: POSIX :: Linux
Classifier: Environment :: GPU
Requires-Python: >=3.9
Description-Content-Type: text/markdown

# kitten-inference-tts2-rocm

The Kitten TTS 2 native engine for AMD Radeon RX 7000 (RDNA3) and RX 9000 (RDNA4) GPUs, for Linux x86_64 and WSL2.
Install it with `pip install "kitten-inference[tts-2-rocm]"`; the Python API is `kitten_inference.tts2`.

Requires the system ROCm 7.x runtime (`libamdhip64.so.7`, see the AMD Radeon guide in the repository). The ROCm
build has no voice cloning. Built for gfx1100;gfx1101;gfx1102;gfx1200;gfx1201.
