Instructions to use KittenML/kitten-tts-2 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 KittenML/kitten-tts-2 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 KittenML/kitten-tts-2 # Run inference directly in the terminal: llama cli -hf KittenML/kitten-tts-2
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf KittenML/kitten-tts-2 # Run inference directly in the terminal: llama cli -hf KittenML/kitten-tts-2
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 KittenML/kitten-tts-2 # Run inference directly in the terminal: ./llama-cli -hf KittenML/kitten-tts-2
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 KittenML/kitten-tts-2 # Run inference directly in the terminal: ./build/bin/llama-cli -hf KittenML/kitten-tts-2
Use Docker
docker model run hf.co/KittenML/kitten-tts-2
- LM Studio
- Jan
- Ollama
How to use KittenML/kitten-tts-2 with Ollama:
ollama run hf.co/KittenML/kitten-tts-2
- Unsloth Desktop
- Docker Model Runner
How to use KittenML/kitten-tts-2 with Docker Model Runner:
docker model run hf.co/KittenML/kitten-tts-2
- Lemonade
How to use KittenML/kitten-tts-2 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull KittenML/kitten-tts-2
Run and chat with the model
lemonade run user.kitten-tts-2-{{QUANT_TAG}}List all available models
lemonade list
- Atomic Chat
Download config.json from KittenML/kitten-tts-2: direct link, hf CLI and curl.
- Browser
- Download file 2.2 kB
-
https://huggingface.co/KittenML/kitten-tts-2/resolve/main/config.json
- Command line
-
hf download hf://KittenML/kitten-tts-2/config.json
-
curl -L -o config.json https://huggingface.co/KittenML/kitten-tts-2/resolve/main/config.json
2.2 kB
| { | |
| "type": "KITTEN2", | |
| "lm_dir": "lm", | |
| "voices": "voices/voices.json", | |
| "speaker_embedding": "speaker/model.safetensors", | |
| "dtype": "bf16", | |
| "speaker_embedding_dim": 512, | |
| "sample_rate": 24000, | |
| "default_voice": "Bruno", | |
| "default_preset": "stable", | |
| "decoders": { | |
| "student_w4": "decoders/student_w4.pt" | |
| }, | |
| "default_decoder": "default", | |
| "decode_presets": { | |
| "stable": { | |
| "temperature": 0.8, | |
| "top_p": 0.8, | |
| "top_k": 50, | |
| "min_p": 0.0 | |
| }, | |
| "expressive": { | |
| "temperature": 0.9, | |
| "top_p": 0.9, | |
| "top_k": 50, | |
| "min_p": 0.0 | |
| } | |
| }, | |
| "generation": { | |
| "use_reference_prompt": true, | |
| "repetition_window": 50, | |
| "emotion_control": "{emo: 1}", | |
| "chunk_chars": 380, | |
| "chunk_min_chars": 130 | |
| }, | |
| "token_map": { | |
| "audio_id_base": 151675, | |
| "num_audio_tokens": 6561, | |
| "speech_start_id": 151669, | |
| "speech_end_id": 151670, | |
| "text_start_id": 151671, | |
| "text_end_id": 151672, | |
| "start_id": 151673, | |
| "stop_id": 151674, | |
| "final_seg_id": 158236, | |
| "reference_speech_start_id": 158237, | |
| "reference_speech_end_id": 158238, | |
| "reference_text_start_id": 158239, | |
| "reference_text_end_id": 158240 | |
| }, | |
| "lm_packed": "lm/model-ternary.safetensors", | |
| "lm_emb4": "lm/model-tl2-emb4.safetensors", | |
| "default_weights": "packed", | |
| "cpp": { | |
| "version": 1, | |
| "gguf": { | |
| "file": "cpp/model-tq2_1.gguf", | |
| "size": 1029076832 | |
| }, | |
| "decoders": { | |
| "default": { | |
| "torchscript": { | |
| "file": "cpp/default/decoder.pt", | |
| "size": 534310697 | |
| }, | |
| "voices": { | |
| "file": "cpp/default/voices.json", | |
| "size": 39235846 | |
| } | |
| }, | |
| "student_w4": { | |
| "torchscript": { | |
| "file": "cpp/student_w4/decoder.pt", | |
| "size": 312339253 | |
| }, | |
| "voices": { | |
| "file": "cpp/student_w4/voices.json", | |
| "size": 16739255 | |
| } | |
| }, | |
| "student_w8": { | |
| "torchscript": { | |
| "file": "cpp/student_w8/decoder.pt", | |
| "size": 312339253 | |
| }, | |
| "voices": { | |
| "file": "cpp/student_w8/voices.json", | |
| "size": 13531964 | |
| } | |
| } | |
| } | |
| } | |
| } |