Text-to-Speech
ONNX
GGUF
Chinese
English
onnxruntime
tts
on-device
jetson
telephony
vits
mb-istft-vits
multi-speaker
mandarin
taiwanese-mandarin
imatrix
conversational
Instructions to use Luigi/PrimeTTS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Luigi/PrimeTTS with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Luigi/PrimeTTS:F32 # Run inference directly in the terminal: llama cli -hf Luigi/PrimeTTS:F32
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Luigi/PrimeTTS:F32 # Run inference directly in the terminal: llama cli -hf Luigi/PrimeTTS:F32
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Luigi/PrimeTTS:F32 # Run inference directly in the terminal: ./llama-cli -hf Luigi/PrimeTTS:F32
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Luigi/PrimeTTS:F32 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Luigi/PrimeTTS:F32
Use Docker
docker model run hf.co/Luigi/PrimeTTS:F32
- LM Studio
- Jan
- Ollama
How to use Luigi/PrimeTTS with Ollama:
ollama run hf.co/Luigi/PrimeTTS:F32
- Unsloth Studio
How to use Luigi/PrimeTTS with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Luigi/PrimeTTS to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Luigi/PrimeTTS to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Luigi/PrimeTTS to start chatting
- Atomic Chat new
- Docker Model Runner
How to use Luigi/PrimeTTS with Docker Model Runner:
docker model run hf.co/Luigi/PrimeTTS:F32
- Lemonade
How to use Luigi/PrimeTTS with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Luigi/PrimeTTS:F32
Run and chat with the model
lemonade run user.PrimeTTS-F32
List all available models
lemonade list
Upload configs/zhtw_mb_istft_16k_v21b.json with huggingface_hub
Browse files
configs/zhtw_mb_istft_16k_v21b.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train": {
|
| 3 |
+
"log_interval": 50,
|
| 4 |
+
"eval_interval": 500,
|
| 5 |
+
"seed": 1234,
|
| 6 |
+
"epochs": 20000,
|
| 7 |
+
"learning_rate": 0.0002,
|
| 8 |
+
"betas": [
|
| 9 |
+
0.8,
|
| 10 |
+
0.99
|
| 11 |
+
],
|
| 12 |
+
"eps": 1e-09,
|
| 13 |
+
"batch_size": 24,
|
| 14 |
+
"fp16_run": false,
|
| 15 |
+
"bf16_run": false,
|
| 16 |
+
"lr_decay": 0.999875,
|
| 17 |
+
"segment_size": 8192,
|
| 18 |
+
"init_lr_ratio": 1,
|
| 19 |
+
"warmup_epochs": 0,
|
| 20 |
+
"c_mel": 45,
|
| 21 |
+
"c_kl": 1.0,
|
| 22 |
+
"fft_sizes": [
|
| 23 |
+
384,
|
| 24 |
+
683,
|
| 25 |
+
171
|
| 26 |
+
],
|
| 27 |
+
"hop_sizes": [
|
| 28 |
+
30,
|
| 29 |
+
60,
|
| 30 |
+
10
|
| 31 |
+
],
|
| 32 |
+
"win_lengths": [
|
| 33 |
+
150,
|
| 34 |
+
300,
|
| 35 |
+
60
|
| 36 |
+
],
|
| 37 |
+
"window": "hann_window",
|
| 38 |
+
"keep_last_ckpts": 40
|
| 39 |
+
},
|
| 40 |
+
"data": {
|
| 41 |
+
"training_files": "/home/luigi/mbvits_run/train_v21b.jsonl",
|
| 42 |
+
"validation_files": "/home/luigi/mbvits_run/val_v21b.jsonl",
|
| 43 |
+
"text_cleaners": [
|
| 44 |
+
"none"
|
| 45 |
+
],
|
| 46 |
+
"max_wav_value": 32768.0,
|
| 47 |
+
"sampling_rate": 16000,
|
| 48 |
+
"filter_length": 1024,
|
| 49 |
+
"hop_length": 256,
|
| 50 |
+
"win_length": 1024,
|
| 51 |
+
"n_mel_channels": 80,
|
| 52 |
+
"mel_fmin": 0.0,
|
| 53 |
+
"mel_fmax": null,
|
| 54 |
+
"add_blank": true,
|
| 55 |
+
"n_speakers": 3,
|
| 56 |
+
"cleaned_text": true,
|
| 57 |
+
"min_phone_len": 4,
|
| 58 |
+
"max_phone_len": 400,
|
| 59 |
+
"max_wav_sec": 15.0
|
| 60 |
+
},
|
| 61 |
+
"model": {
|
| 62 |
+
"ms_istft_vits": false,
|
| 63 |
+
"mb_istft_vits": true,
|
| 64 |
+
"istft_vits": false,
|
| 65 |
+
"subbands": 4,
|
| 66 |
+
"gen_istft_n_fft": 16,
|
| 67 |
+
"gen_istft_hop_size": 4,
|
| 68 |
+
"inter_channels": 192,
|
| 69 |
+
"hidden_channels": 192,
|
| 70 |
+
"filter_channels": 768,
|
| 71 |
+
"n_heads": 2,
|
| 72 |
+
"n_layers": 6,
|
| 73 |
+
"kernel_size": 3,
|
| 74 |
+
"p_dropout": 0.1,
|
| 75 |
+
"resblock": "1",
|
| 76 |
+
"resblock_kernel_sizes": [
|
| 77 |
+
3,
|
| 78 |
+
7,
|
| 79 |
+
11
|
| 80 |
+
],
|
| 81 |
+
"resblock_dilation_sizes": [
|
| 82 |
+
[
|
| 83 |
+
1,
|
| 84 |
+
3,
|
| 85 |
+
5
|
| 86 |
+
],
|
| 87 |
+
[
|
| 88 |
+
1,
|
| 89 |
+
3,
|
| 90 |
+
5
|
| 91 |
+
],
|
| 92 |
+
[
|
| 93 |
+
1,
|
| 94 |
+
3,
|
| 95 |
+
5
|
| 96 |
+
]
|
| 97 |
+
],
|
| 98 |
+
"upsample_rates": [
|
| 99 |
+
4,
|
| 100 |
+
4
|
| 101 |
+
],
|
| 102 |
+
"upsample_initial_channel": 512,
|
| 103 |
+
"upsample_kernel_sizes": [
|
| 104 |
+
16,
|
| 105 |
+
16
|
| 106 |
+
],
|
| 107 |
+
"n_layers_q": 3,
|
| 108 |
+
"use_spectral_norm": false,
|
| 109 |
+
"use_sdp": false,
|
| 110 |
+
"num_tones": 6,
|
| 111 |
+
"num_langs": 2,
|
| 112 |
+
"n_speakers": 3,
|
| 113 |
+
"gin_channels": 256
|
| 114 |
+
}
|
| 115 |
+
}
|