AuK-Base-and-Flash-GGUF

These GGUF files are for use with [audio.cpp](https://github.com/0xShug0/audio.cpp). The card's `base_model` points to the [Tencent AuK base model](https://huggingface.co/tencent/AuK). This package also includes optional files converted from [AuK-Flash](https://huggingface.co/tencent/AuK-Flash); Flash is a separate distilled variant and is not the pinned base model. > **Output quality:** We validate parity with upstream Python for the tested configuration, not whether AuK's output meets every quality expectation. If a result is disappointing, listen to the corresponding Python reference WAV linked below first. A similar Python result points to the upstream model's behavior, not necessarily an audio.cpp conversion issue. The quantized component combinations have not received the same 16-task parity validation. Pass the downloaded directory to `audiocpp_cli --model`. Keep the `config/` and `tokenizer/` directories alongside the GGUF files. The default components are `auk-base-f32.gguf`, `qwen2.5-omni-3b-bf16.gguf`, and `auk-vae-f32.gguf`. AuK-Flash requires `--session-option auk.variant=flash`; its default generator is `auk-flash-f32.gguf`. The Qwen component is Qwen2.5-Omni-3B. For example, instruction TTS with explicitly selected Base components: audiocpp_cli --task tts --family auk \ --model /path/to/AuK-Base-and-Flash-GGUF --backend cuda \ --session-option auk.variant=base \ --session-option auk.model_gguf=auk-base-f32.gguf \ --session-option auk.qwen_gguf=qwen2.5-omni-3b-bf16.gguf \ --session-option auk.vae_gguf=auk-vae-f32.gguf \ --text "The next train leaves in ten minutes." \ --request-option "instruct=A warm male voice speaking clear English." \ --request-option duration_sec=4 --seed 42 --log --out speech.wav To use AuK-Flash, select `auk.variant=flash` and an `auk-flash-*.gguf` generator. To use the Qwen Q8_0 component, select `auk.qwen_gguf=qwen2.5-omni-3b-q8_0.gguf`. Keep the F32 VAE in either case. For editing, use `--task gen --audio input.wav --text "<editing instruction>"`. See the [audio.cpp AuK guide](https://github.com/0xShug0/audio.cpp/blob/main/docs/models/auk.md) and the [AuK cookbook](https://github.com/Tencent-Hunyuan/AuK/blob/main/docs/COOKBOOK.md) for request options and example instructions. The 16-task C++/Python comparison forced FP32 inference and disabled TF32 in both implementations. Input audio and reference voices came from the [upstream AuK demo assets](https://github.com/Tencent-Hunyuan/AuK/tree/main/assets/demo-input-audio). Durations not shown below matched the source recording. All 16 C++ requests completed and produced 24 kHz WAVs with the same frame counts as the Python outputs. The cosine values compare C++ WAVs with the Python baseline. Waveform cosine alone does not establish whether an edit followed its instruction. The no-TF32 C++ run matched the Python WAVs at waveform cosine 0.999989991 or higher for all 16 tasks; the files were not byte-identical. These historical results use the original combined GGUF and are **not** a 16-task parity claim for the component GGUFs in this package. All component smoke tests used CUDA and the F32 VAE. A pass here means the listed task loaded the selected GGUFs and generated a WAV; it does not establish Python parity or task quality. The Base F16 + Qwen Q8_0 and AuK-Flash Q8_0 + Qwen Q8_0 combinations were **not tested**.