Automatic Speech Recognition
llama-cpp-python
GGUF
English
speech-to-speech
faster-whisper
qwen
windows
local-ai
terminal
sapi
Instructions to use maytman12/s2s-complete-setup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use maytman12/s2s-complete-setup with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="maytman12/s2s-complete-setup", filename="{{GGUF_FILE}}", )output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
| { | |
| "stt_model": "medium", | |
| "stt_device": "auto", | |
| "stt_compute_type": "auto", | |
| "record_seconds": 4, | |
| "sample_rate": 16000, | |
| "llm_repo_id": "bartowski/Qwen2.5-3B-Instruct-GGUF", | |
| "llm_filename": "Qwen2.5-3B-Instruct-Q4_K_M.gguf", | |
| "llm_model_path": "models/llm/qwen2.5-3b-instruct-q4_k_m.gguf", | |
| "llm_context_size": 2048, | |
| "llm_gpu_layers": "auto", | |
| "llm_temperature": 0.35, | |
| "llm_max_tokens": 140, | |
| "tts_model": "tts_models/en/ljspeech/vits", | |
| "system_prompt": "You are a concise local voice assistant. Answer in one or two short sentences." | |
| } |