Duplicate from walusungungulube/ghana-tts-36k-gguf

Co-authored-by: Walusungu Lulukile Ngulube <walusungungulube@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,42 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+ghana-tts-36k-f16-audiovae-f16.gguf filter=lfs diff=lfs merge=lfs -text
+ghana-tts-36k-f16.gguf filter=lfs diff=lfs merge=lfs -text
+ghana-tts-36k-q4_k-audiovae-f16.gguf filter=lfs diff=lfs merge=lfs -text
+ghana-tts-36k-q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+ghana-tts-36k-q8_0-audiovae-f16.gguf filter=lfs diff=lfs merge=lfs -text
+ghana-tts-36k-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+ghana-tts-36k-f32.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+license: mit
+tags:
+  - text-to-speech
+  - voxcpm
+  - gguf
+  - ghana-tts
+base_model: ghananlpcommunity/ghana-tts-36k
+---
+
+# ghana-tts-36k — GGUF quantized variants
+
+GGUF conversions of [`ghananlpcommunity/ghana-tts-36k`](https://huggingface.co/ghananlpcommunity/ghana-tts-36k)
+for use with [bluryar/VoxCPM.cpp](https://github.com/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.
+
+## Files
+
+| 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 |
+
+## Which one to use
+
+Based on [bluryar/VoxCPM.cpp](https://github.com/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:**
+- Default pick: **`ghana-tts-36k-q8_0.gguf`** — best full-pipeline RTF at this model scale on CPU.
+- Smaller/faster, slight accuracy trade-off: `ghana-tts-36k-q4_k-audiovae-f16.gguf`.
+
+**GPU (CUDA) inference:**
+- Default pick: **`ghana-tts-36k-q8_0-audiovae-f16.gguf`** — best full-pipeline RTF at this model scale on CUDA.
+- Smallest CUDA-friendly option: `ghana-tts-36k-q4_k-audiovae-f16.gguf`.
+
+## Inference
+
+This repo includes two scripts that build and run [VoxCPM.cpp](https://github.com/bluryar/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
+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.

ghana-tts-36k-f16-audiovae-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4718cb4d6e9620ca89173c969d9b0138f3775538f3a4a3a55351816daf8ca16d
+size 1460771872

ghana-tts-36k-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4718cb4d6e9620ca89173c969d9b0138f3775538f3a4a3a55351816daf8ca16d
+size 1460771872

ghana-tts-36k-f32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77baf8801bdbe1cd77ca2ea1095f903bed3373fec6bef90b5b511032a09018ee
+size 2913602336

ghana-tts-36k-q4_k-audiovae-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7227bee9a187c1905f505943330e1c144be8e4d03c602c10801392e938f6b7
+size 571242016

ghana-tts-36k-q4_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc677f558f24a0ad23f4f29148a5cfdf63763f8ba74b66fdf4d5d5bc6afbcd0
+size 499832224

ghana-tts-36k-q8_0-audiovae-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552b37352bf215a1fb31c0b13bed2105793551853c504f21c1bd994a7c4f02cf
+size 850327072

ghana-tts-36k-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3668d62ab177b24fbf99deb08993029df8d91d09ae5cc45296ce8011bf355617
+size 803072768

infer_cpu.sh

@@ -0,0 +1,38 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# CPU inference for ghana-tts-36k via VoxCPM.cpp
+# Usage: bash infer_cpu.sh "text" prompt.wav "prompt transcript" out.wav
+
+TEXT="${1:?text required}"
+PROMPT_AUDIO="${2:?prompt audio path required}"
+PROMPT_TEXT="${3:?prompt transcript required}"
+OUTPUT="${4:-out.wav}"
+
+MODEL_PATH="$(dirname "$0")/ghana-tts-36k-q8_0.gguf"   # recommended CPU variant
+THREADS="${THREADS:-4}"
+
+if [ ! -d VoxCPM.cpp ]; then
+    git clone --depth 1 https://github.com/bluryar/VoxCPM.cpp.git
+fi
+
+if [ ! -f VoxCPM.cpp/build-cpu/examples/voxcpm_tts ]; then
+    cmake -S VoxCPM.cpp -B VoxCPM.cpp/build-cpu -G Ninja \
+        -DCMAKE_BUILD_TYPE=Release \
+        -DVOXCPM_CUDA=OFF \
+        -DVOXCPM_BUILD_TESTS=OFF \
+        -DVOXCPM_BUILD_WASM=OFF \
+        -DVOXCPM_BUILD_BENCHMARK=OFF
+    cmake --build VoxCPM.cpp/build-cpu --target voxcpm_tts -j"$(nproc)"
+fi
+
+VoxCPM.cpp/build-cpu/examples/voxcpm_tts \
+    --text "$TEXT" \
+    --prompt-audio "$PROMPT_AUDIO" \
+    --prompt-text "$PROMPT_TEXT" \
+    --output "$OUTPUT" \
+    --model-path "$MODEL_PATH" \
+    --backend cpu \
+    --threads "$THREADS"
+
+echo "Wrote $OUTPUT"

infer_gpu.sh

@@ -0,0 +1,44 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# CUDA inference for ghana-tts-36k via VoxCPM.cpp
+# Requires an NVIDIA GPU + CUDA toolkit (nvcc) on this machine.
+# Usage: bash infer_gpu.sh "text" prompt.wav "prompt transcript" out.wav
+
+TEXT="${1:?text required}"
+PROMPT_AUDIO="${2:?prompt audio path required}"
+PROMPT_TEXT="${3:?prompt transcript required}"
+OUTPUT="${4:-out.wav}"
+
+MODEL_PATH="$(dirname "$0")/ghana-tts-36k-q8_0-audiovae-f16.gguf"   # recommended GPU variant
+THREADS="${THREADS:-4}"
+
+if ! command -v nvcc >/dev/null 2>&1; then
+    echo "nvcc not found — this script requires a CUDA toolkit installed." >&2
+    exit 1
+fi
+
+if [ ! -d VoxCPM.cpp ]; then
+    git clone --depth 1 https://github.com/bluryar/VoxCPM.cpp.git
+fi
+
+if [ ! -f VoxCPM.cpp/build-cuda/examples/voxcpm_tts ]; then
+    cmake -S VoxCPM.cpp -B VoxCPM.cpp/build-cuda -G Ninja \
+        -DCMAKE_BUILD_TYPE=Release \
+        -DVOXCPM_CUDA=ON \
+        -DVOXCPM_BUILD_TESTS=OFF \
+        -DVOXCPM_BUILD_WASM=OFF \
+        -DVOXCPM_BUILD_BENCHMARK=OFF
+    cmake --build VoxCPM.cpp/build-cuda --target voxcpm_tts -j"$(nproc)"
+fi
+
+VoxCPM.cpp/build-cuda/examples/voxcpm_tts \
+    --text "$TEXT" \
+    --prompt-audio "$PROMPT_AUDIO" \
+    --prompt-text "$PROMPT_TEXT" \
+    --output "$OUTPUT" \
+    --model-path "$MODEL_PATH" \
+    --backend cuda \
+    --threads "$THREADS"
+
+echo "Wrote $OUTPUT"