Instructions to use xsingh/Voce-Mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Zonos
How to use xsingh/Voce-Mini with Zonos:
# pip install git+https://github.com/Zyphra/Zonos.git import torchaudio from zonos.model import Zonos from zonos.conditioning import make_cond_dict model = Zonos.from_pretrained("xsingh/Voce-Mini", device="cuda") wav, sr = torchaudio.load("speaker.wav") # 5-10s reference clip speaker = model.make_speaker_embedding(wav, sr) cond = make_cond_dict(text="Hello, world!", speaker=speaker, language="en-us") codes = model.generate(model.prepare_conditioning(cond)) audio = model.autoencoder.decode(codes)[0].cpu() torchaudio.save("sample.wav", audio, model.autoencoder.sampling_rate) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use xsingh/Voce-Mini 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 xsingh/Voce-Mini # Run inference directly in the terminal: llama cli -hf xsingh/Voce-Mini
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf xsingh/Voce-Mini # Run inference directly in the terminal: llama cli -hf xsingh/Voce-Mini
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf xsingh/Voce-Mini # Run inference directly in the terminal: ./build/bin/llama cli -hf xsingh/Voce-Mini
Use Docker
docker model run hf.co/xsingh/Voce-Mini
- Llama new
- LM Studio
- Jan
- Ollama
How to use xsingh/Voce-Mini with Ollama:
ollama run hf.co/xsingh/Voce-Mini
- Unsloth Desktop
- Docker Model Runner
How to use xsingh/Voce-Mini with Docker Model Runner:
docker model run hf.co/xsingh/Voce-Mini
- Lemonade
How to use xsingh/Voce-Mini with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull xsingh/Voce-Mini
Run and chat with the model
lemonade run user.Voce-Mini-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Download lm/zonos3_mini/params.json from xsingh/Voce-Mini: direct link, hf CLI and curl.
- Browser
- Download file 2.5 kB
-
https://huggingface.co/xsingh/Voce-Mini/resolve/main/lm/zonos3_mini/params.json
- Command line
-
hf download hf://xsingh/Voce-Mini/lm/zonos3_mini/params.json
-
curl -L -o params.json https://huggingface.co/xsingh/Voce-Mini/resolve/main/lm/zonos3_mini/params.json
2.5 kB
| { | |
| "model": { | |
| "n_layers": 11, | |
| "dim": 1024, | |
| "head_dim": 32, | |
| "n_heads": 16, | |
| "n_kv_heads": 4, | |
| "ffn_dim_multiplier": 2.0, | |
| "multiple_of": 64, | |
| "moe_ffn_dim_multiplier": 1.5, | |
| "moe_multiple_of": 64, | |
| "norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "max_seqlen": 32768, | |
| "n_codebooks": 10, | |
| "codebook_size": 4096, | |
| "codebook_sizes": [ | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096, | |
| 4096 | |
| ], | |
| "eoa_id": 4096, | |
| "audio_pad_id": 4097, | |
| "text_vocab": 8196, | |
| "speaker_enabled": true, | |
| "speaker_embedding_dim": 192, | |
| "attention_pattern": "gdn3_global1", | |
| "use_xsa": false, | |
| "residual_type": "full_attnres", | |
| "block_attnres_block_size": 4, | |
| "moe_router_topk": 2, | |
| "moe_n_experts": 64, | |
| "moe_alpha": 0.25, | |
| "moe_router_dim": 128, | |
| "moe_router_type": "linear", | |
| "moe_router_use_eda": false, | |
| "moe_balancing_strategy": "quantile", | |
| "moe_start_from_layer": 1, | |
| "moe_end_from_layer": 0, | |
| "loss_softcap": 15.0, | |
| "condition_tokens_enabled": true, | |
| "condition_n_buckets": 10, | |
| "condition_count": 3, | |
| "condition_bucket_counts": [ | |
| 10, | |
| 10, | |
| 30 | |
| ], | |
| "text_tokenizer_spec": { | |
| "kind": "superbpe", | |
| "path": "tokenizer/superbpe8192.json", | |
| "sha256": "90322f910600027dee7fe63d400d1d9dc1035c167d560aadf0871e3661d08bf3", | |
| "vocab_size": 8192, | |
| "offset": 4, | |
| "bos": 2, | |
| "eos": 3 | |
| }, | |
| "audio_codec": "opus_dual_3n_600k_sched600k_r4096_step600000", | |
| "speaker_embedding_codec": "ownmect_s2", | |
| "speaker_reference_prefix_enabled": true, | |
| "speaker_reference_max_seconds": 60.0, | |
| "condition_names": [ | |
| "loudness", | |
| "fmax", | |
| "speaking_rate" | |
| ], | |
| "condition_edges": { | |
| "loudness": [ | |
| -29.778, | |
| -26.947, | |
| -25.047, | |
| -23.3, | |
| -21.743, | |
| -20.386, | |
| -19.186, | |
| -17.851, | |
| -15.967 | |
| ], | |
| "fmax": [ | |
| 8437.5, | |
| 10242.2, | |
| 11507.8, | |
| 13359.4, | |
| 15164.1, | |
| 15585.9, | |
| 15750.0, | |
| 17765.6, | |
| 19945.3 | |
| ], | |
| "speaking_rate": [ | |
| 6.546, | |
| 8.182, | |
| 9.273, | |
| 10.31, | |
| 11.054, | |
| 11.667, | |
| 12.193, | |
| 12.656, | |
| 13.083, | |
| 13.476, | |
| 13.846, | |
| 14.196, | |
| 14.53, | |
| 14.887, | |
| 15.193, | |
| 15.517, | |
| 15.865, | |
| 16.208, | |
| 16.579, | |
| 16.972, | |
| 17.411, | |
| 17.898, | |
| 18.434, | |
| 19.069, | |
| 19.818, | |
| 20.816, | |
| 22.286, | |
| 24.722, | |
| 29.25 | |
| ] | |
| }, | |
| "condition_units": { | |
| "loudness": "LUFS", | |
| "fmax": "Hz", | |
| "speaking_rate": "utf-8 bytes per second" | |
| }, | |
| "model_type": "zonos2", | |
| "dtype": "bfloat16", | |
| "norm_topk_prob": true, | |
| "moe_impl": "sonic" | |
| } | |
| } | |