Instructions to use slojoe4real/TX-VOICE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Moshi
How to use slojoe4real/TX-VOICE with Moshi:
# pip install moshi # Run the interactive web server python -m moshi.server --hf-repo "slojoe4real/TX-VOICE" # Then open https://localhost:8998 in your browser
# pip install moshi import torch from moshi.models import loaders # Load checkpoint info from HuggingFace checkpoint = loaders.CheckpointInfo.from_hf_repo("slojoe4real/TX-VOICE") # Load the Mimi audio codec mimi = checkpoint.get_mimi(device="cuda") mimi.set_num_codebooks(8) # Encode audio (24kHz, mono) wav = torch.randn(1, 1, 24000 * 10) # [batch, channels, samples] with torch.no_grad(): codes = mimi.encode(wav.cuda()) decoded = mimi.decode(codes) - Notebooks
- Google Colab
- Kaggle
Commit ·
d6c9dce
0
Parent(s):
Duplicate from Tarxxxxxx/TX-VOICE
Browse filesCo-authored-by: John Wantz Jr. <wantzjt@users.noreply.huggingface.co>
- .gitattributes +36 -0
- README.md +105 -0
- model.q8.gguf +3 -0
- tokenizer-e351c8d8-checkpoint125.safetensors +3 -0
- tokenizer_spm_32k_3.model +3 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
model.q8.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- voice
|
| 7 |
+
- speech
|
| 8 |
+
- tts
|
| 9 |
+
- local
|
| 10 |
+
- privacy
|
| 11 |
+
- tarx
|
| 12 |
+
- moshi
|
| 13 |
+
library_name: candle
|
| 14 |
+
pipeline_tag: text-to-speech
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# TX-VOICE: Local-First Voice for TARX
|
| 18 |
+
|
| 19 |
+
**Private voice AI that runs entirely on your machine. No cloud. No latency. No data leaving your device.**
|
| 20 |
+
|
| 21 |
+
## Overview
|
| 22 |
+
|
| 23 |
+
TX-VOICE is TARX's voice model optimized for local execution. Built on the Moshi architecture and quantized to Q8 for efficient inference on consumer hardware.
|
| 24 |
+
|
| 25 |
+
| Spec | Value |
|
| 26 |
+
|------|-------|
|
| 27 |
+
| **Size** | 7.2 GB |
|
| 28 |
+
| **Format** | GGUF Q8 |
|
| 29 |
+
| **Architecture** | Moshi (Kyutai) |
|
| 30 |
+
| **Min RAM** | 16 GB |
|
| 31 |
+
| **Recommended** | 32 GB+ RAM, Apple Silicon or NVIDIA GPU |
|
| 32 |
+
|
| 33 |
+
## Features
|
| 34 |
+
|
| 35 |
+
- **Real-time voice synthesis** - Low-latency text-to-speech
|
| 36 |
+
- **100% local** - No internet required after download
|
| 37 |
+
- **Privacy-first** - Your voice data never leaves your machine
|
| 38 |
+
- **Hardware-optimized** - Leverages Metal (macOS) or CUDA (NVIDIA)
|
| 39 |
+
|
| 40 |
+
## Quick Start
|
| 41 |
+
|
| 42 |
+
### With TARX Workbench
|
| 43 |
+
|
| 44 |
+
TX-VOICE is automatically configured in TARX Workbench. Just enable voice in settings.
|
| 45 |
+
|
| 46 |
+
### Standalone Usage
|
| 47 |
+
|
| 48 |
+
```bash
|
| 49 |
+
# Clone the tarx-voice service
|
| 50 |
+
git clone https://github.com/tarx-ai/tarx-voice
|
| 51 |
+
cd tarx-voice
|
| 52 |
+
|
| 53 |
+
# Build and run
|
| 54 |
+
cargo build --release
|
| 55 |
+
./target/release/tarx-voice --model TX-VOICE
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
### WebSocket API
|
| 59 |
+
|
| 60 |
+
TX-VOICE runs on port `11438` by default:
|
| 61 |
+
|
| 62 |
+
```javascript
|
| 63 |
+
const ws = new WebSocket('ws://localhost:11438');
|
| 64 |
+
ws.send(JSON.stringify({ text: "Hello, world!" }));
|
| 65 |
+
```
|
| 66 |
+
|
| 67 |
+
## Hardware Requirements
|
| 68 |
+
|
| 69 |
+
| Hardware | Performance |
|
| 70 |
+
|----------|-------------|
|
| 71 |
+
| Apple M1/M2/M3/M4 | Excellent (Metal acceleration) |
|
| 72 |
+
| NVIDIA RTX 30/40 | Excellent (CUDA acceleration) |
|
| 73 |
+
| Intel/AMD CPU | Good (AVX2 optimized) |
|
| 74 |
+
|
| 75 |
+
## Integration
|
| 76 |
+
|
| 77 |
+
TX-VOICE integrates with:
|
| 78 |
+
|
| 79 |
+
- **TARX Workbench** - Desktop AI assistant
|
| 80 |
+
- **TARX Code-OSS** - VS Code extension
|
| 81 |
+
- **Custom apps** - WebSocket API
|
| 82 |
+
|
| 83 |
+
## Architecture
|
| 84 |
+
|
| 85 |
+
Based on Kyutai's Moshi model, optimized for local inference:
|
| 86 |
+
|
| 87 |
+
- Streaming audio generation
|
| 88 |
+
- Low memory footprint via Q8 quantization
|
| 89 |
+
- Rust-native inference via Candle
|
| 90 |
+
|
| 91 |
+
## License
|
| 92 |
+
|
| 93 |
+
Apache 2.0 - Free for personal and commercial use.
|
| 94 |
+
|
| 95 |
+
## Links
|
| 96 |
+
|
| 97 |
+
- [TARX Website](https://tarx.com)
|
| 98 |
+
- [TARX Workbench](https://github.com/tarx-ai/tarx-workbench)
|
| 99 |
+
- [Documentation](https://tarx.com/docs)
|
| 100 |
+
|
| 101 |
+
---
|
| 102 |
+
|
| 103 |
+
**Part of the TARX local-first AI platform.**
|
| 104 |
+
|
| 105 |
+
TX-8G | TX-12G | TX-16G | TX-M-72B | **TX-VOICE**
|
model.q8.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a48355349fd6199dbf9bd989595b8d6f44e5bc6d8ebeefb95f2e410cce19784e
|
| 3 |
+
size 8169420704
|
tokenizer-e351c8d8-checkpoint125.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09b782f0629851a271227fb9d36db65c041790365f11bbe5d3d59369cf863f50
|
| 3 |
+
size 384644900
|
tokenizer_spm_32k_3.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78d4336533ddc26f9acf7250d7fb83492152196c6ea4212c841df76933f18d2d
|
| 3 |
+
size 552778
|