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
Rebuild the llama.cpp assets for the mixed_v1_rl checkpoint
Browse filesmodel-tq2_1.gguf is re-exported from the new weights. The voices files carry spk_proj(embedding), which is part of the LM checkpoint, so their speaker vectors are refreshed too; everything codec-side is unchanged.
default and student_w4 now cover all 47 voices. student_w8 keeps its 38, since the repository ships no w8 flow weights to re-derive the rest.
- config.json +4 -4
- cpp/default/voices.json +2 -2
- cpp/model-tq2_1.gguf +1 -1
- cpp/student_w4/voices.json +2 -2
- cpp/student_w8/voices.json +2 -2
config.json
CHANGED
|
@@ -65,7 +65,7 @@
|
|
| 65 |
},
|
| 66 |
"voices": {
|
| 67 |
"file": "cpp/default/voices.json",
|
| 68 |
-
"size":
|
| 69 |
}
|
| 70 |
},
|
| 71 |
"student_w4": {
|
|
@@ -75,7 +75,7 @@
|
|
| 75 |
},
|
| 76 |
"voices": {
|
| 77 |
"file": "cpp/student_w4/voices.json",
|
| 78 |
-
"size":
|
| 79 |
}
|
| 80 |
},
|
| 81 |
"student_w8": {
|
|
@@ -85,9 +85,9 @@
|
|
| 85 |
},
|
| 86 |
"voices": {
|
| 87 |
"file": "cpp/student_w8/voices.json",
|
| 88 |
-
"size":
|
| 89 |
}
|
| 90 |
}
|
| 91 |
}
|
| 92 |
}
|
| 93 |
-
}
|
|
|
|
| 65 |
},
|
| 66 |
"voices": {
|
| 67 |
"file": "cpp/default/voices.json",
|
| 68 |
+
"size": 39235846
|
| 69 |
}
|
| 70 |
},
|
| 71 |
"student_w4": {
|
|
|
|
| 75 |
},
|
| 76 |
"voices": {
|
| 77 |
"file": "cpp/student_w4/voices.json",
|
| 78 |
+
"size": 16739255
|
| 79 |
}
|
| 80 |
},
|
| 81 |
"student_w8": {
|
|
|
|
| 85 |
},
|
| 86 |
"voices": {
|
| 87 |
"file": "cpp/student_w8/voices.json",
|
| 88 |
+
"size": 13531964
|
| 89 |
}
|
| 90 |
}
|
| 91 |
}
|
| 92 |
}
|
| 93 |
+
}
|
cpp/default/voices.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2fbe5106d939f59b964e7780951dc402f89aceddd113b82e0539a5a2928c1ff
|
| 3 |
+
size 39235846
|
cpp/model-tq2_1.gguf
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1029076832
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84f0a8b9986fbc01fbe6d4777703304d1cecc7b99e8c6fd2c607e0661e804d4c
|
| 3 |
size 1029076832
|
cpp/student_w4/voices.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cd23287a80ff2ec558a5c4b90e65a2755ecd675bf72a40459afb16e3c0bd573
|
| 3 |
+
size 16739255
|
cpp/student_w8/voices.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a520b8e86830f8d4371db66f416a8ad491c14d6f2b1a1d4a41f704a4a7ab787
|
| 3 |
+
size 13531964
|