Instructions to use KavirLabs/Darya_TTS 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 KavirLabs/Darya_TTS 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 KavirLabs/Darya_TTS:Q8_0 # Run inference directly in the terminal: llama cli -hf KavirLabs/Darya_TTS:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf KavirLabs/Darya_TTS:Q8_0 # Run inference directly in the terminal: llama cli -hf KavirLabs/Darya_TTS:Q8_0
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 KavirLabs/Darya_TTS:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf KavirLabs/Darya_TTS:Q8_0
Use Docker
docker model run hf.co/KavirLabs/Darya_TTS:Q8_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use KavirLabs/Darya_TTS with Ollama:
ollama run hf.co/KavirLabs/Darya_TTS:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use KavirLabs/Darya_TTS with Docker Model Runner:
docker model run hf.co/KavirLabs/Darya_TTS:Q8_0
- Lemonade
How to use KavirLabs/Darya_TTS with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull KavirLabs/Darya_TTS:Q8_0
Run and chat with the model
lemonade run user.Darya_TTS-Q8_0
List all available models
lemonade list
- Atomic Chat
Use the dune codec only; drop dead takane/kanadec imports
Browse files- ONNX/onnx_cleaned.ipynb +1 -3
ONNX/onnx_cleaned.ipynb
CHANGED
|
@@ -173,7 +173,6 @@
|
|
| 173 |
"\n",
|
| 174 |
"from inference_utils_darya import *\n",
|
| 175 |
"from inference_utils import *\n",
|
| 176 |
-
"from src_takane_nano.codec.audio_processing.kanadec_audio_tokenizer import load_nemo_nano_audio_tokenizer\n",
|
| 177 |
"from transformers import AutoTokenizer\n",
|
| 178 |
"tokenizer_path = \"KavirLabs/Darya_Tokenizer_bpe\"\n",
|
| 179 |
"tokenizer = AutoTokenizer.from_pretrained(tokenizer_path, add_bos_token=True, add_eos_token=True)\n",
|
|
@@ -559,7 +558,6 @@
|
|
| 559 |
"\n",
|
| 560 |
"from inference_utils_darya import *\n",
|
| 561 |
"from inference_utils import *\n",
|
| 562 |
-
"from src_takane_nano.codec.audio_processing.kanadec_audio_tokenizer import load_nemo_nano_audio_tokenizer\n",
|
| 563 |
"from transformers import AutoTokenizer\n",
|
| 564 |
"\n",
|
| 565 |
"tokenizer_path = \"KavirLabs/Darya_Tokenizer_bpe\"\n",
|
|
@@ -796,4 +794,4 @@
|
|
| 796 |
},
|
| 797 |
"nbformat": 4,
|
| 798 |
"nbformat_minor": 5
|
| 799 |
-
}
|
|
|
|
| 173 |
"\n",
|
| 174 |
"from inference_utils_darya import *\n",
|
| 175 |
"from inference_utils import *\n",
|
|
|
|
| 176 |
"from transformers import AutoTokenizer\n",
|
| 177 |
"tokenizer_path = \"KavirLabs/Darya_Tokenizer_bpe\"\n",
|
| 178 |
"tokenizer = AutoTokenizer.from_pretrained(tokenizer_path, add_bos_token=True, add_eos_token=True)\n",
|
|
|
|
| 558 |
"\n",
|
| 559 |
"from inference_utils_darya import *\n",
|
| 560 |
"from inference_utils import *\n",
|
|
|
|
| 561 |
"from transformers import AutoTokenizer\n",
|
| 562 |
"\n",
|
| 563 |
"tokenizer_path = \"KavirLabs/Darya_Tokenizer_bpe\"\n",
|
|
|
|
| 794 |
},
|
| 795 |
"nbformat": 4,
|
| 796 |
"nbformat_minor": 5
|
| 797 |
+
}
|