stt-qwen3-0.6b-merged-GGUF/README.md

license, datasets, language, base_model, pipeline_tag, tags, model-index

license	datasets	language	base_model	pipeline_tag	tags	model-index
mit	aldigobbler/stt-correction	en	aldigobbler/stt-qwen3-0.6b-merged	text-generation	speech-to-text error-correction text-cleaning llama-cpp gguf-my-repo	name results STT Error Correction Model task dataset metrics type name text-generation STT Error Correction name type split stt-correction aldigobbler/stt-correction validation type value name loss 5.0712228 Validation Loss

stt-qwen3-0.6b-merged

Model creator: aldigobbler
Original model: aldigobbler/stt-qwen3-0.6b-merged
GGUF quantization: provided by aldigobbler using llama.cpp

Special thanks

🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.

Use with Ollama

ollama run "hf.co/aldigobbler/stt-qwen3-0.6b-merged-GGUF:Q8_0"

Use with LM Studio

lms load "aldigobbler/stt-qwen3-0.6b-merged-GGUF"

Use with llama.cpp CLI

llama-cli --hf "aldigobbler/stt-qwen3-0.6b-merged-GGUF:Q8_0" -p "The meaning to life and the universe is"

Use with llama.cpp Server:

llama-server --hf "aldigobbler/stt-qwen3-0.6b-merged-GGUF:Q8_0" -c 4096