Downloads · 30 days
208
38% of all-time downloads
ghananlpcommunity/ghana-tts-36k-gguf
ghana-tts-36k-gguf is a text-to-speech model from ghananlpcommunity. Use it when you need text read aloud. It is set up for voxcpm. The card lists the license as mit.
GGUF conversions of ghananlpcommunity/ghana-tts-36k for use with bluryar/VoxCPM.cpp.
Downloads · 30 days
208
38% of all-time downloads
All-time downloads
549
Public
Repo size
7.1 GB
Likes
0
Public
Click a slice to open those files.
.gguf8.6 GB · 100%
From the Hugging Face model README
GGUF conversions of ghananlpcommunity/ghana-tts-36k
for use with bluryar/VoxCPM.cpp.
The .gguf files are backend-agnostic — the same file runs on both a CPU-only
and a CUDA build of the inference engine. Only the binary you compile differs
between CPU and GPU deployment, not the weight file.
| File | Quant | AudioVAE | Size | Notes |
|---|---|---|---|---|
ghana-tts-36k-f32.gguf | F32 | original | largest | Reference/max-accuracy baseline |
ghana-tts-36k-f16.gguf | F16 | mixed | ||
ghana-tts-36k-f16-audiovae-f16.gguf | F16 | f16 | ||
ghana-tts-36k-q8_0.gguf | Q8_0 | mixed | Recommended for CPU | |
ghana-tts-36k-q8_0-audiovae-f16.gguf | Q8_0 | f16 | Recommended for GPU (CUDA) | |
ghana-tts-36k-q4_k.gguf | Q4_K | mixed | Smallest, more accuracy loss | |
ghana-tts-36k-q4_k-audiovae-f16.gguf | Q4_K | f16 | smallest of the practical options | Fastest CPU model-only RTF; good compact CUDA option too |
Based on bluryar/VoxCPM.cpp's own published
benchmarks on the same "voxcpm" architecture family (not run on this exact
checkpoint — validate on your own audio before committing to one in production):
CPU inference:
ghana-tts-36k-q8_0.gguf — best full-pipeline RTF at this model scale on CPU.ghana-tts-36k-q4_k-audiovae-f16.gguf.GPU (CUDA) inference:
ghana-tts-36k-q8_0-audiovae-f16.gguf — best full-pipeline RTF at this model scale on CUDA.ghana-tts-36k-q4_k-audiovae-f16.gguf.This repo includes two scripts that build and run VoxCPM.cpp against these weights:
infer_cpu.sh — builds a CPU-only voxcpm_tts and runs it against ghana-tts-36k-q8_0.gguf.infer_gpu.sh — builds a CUDA-enabled voxcpm_tts (requires an NVIDIA GPU + CUDA toolkit) and runs it against ghana-tts-36k-q8_0-audiovae-f16.gguf.Usage (either script):
bash infer_cpu.sh "Text to synthesize" prompt.wav "Exact transcript of prompt.wav" out.wav
bash infer_gpu.sh "Text to synthesize" prompt.wav "Exact transcript of prompt.wav" out.wav
Swap in a different .gguf from this repo by editing the MODEL_PATH variable
at the top of either script.