Automatic Speech Recognition
Safetensors
English
speech-to-text
canary-qwen
nvidia
qwen
optimum-quanto
qint8
int8
open-webui
openai-compatible
rtx-5090
quanto
quantized
openwebui
1.7gb
audio-encoder-unquantized
llm-only-quant
asr-preserved
systemd
fastapi
webm-opus
browser-mic
quanto-qint8
qint8-safetensors
8-bit precision
8bit
File size: 272 Bytes
33374e3 | 1 2 3 4 5 6 7 8 9 10 | # Quantized Artifacts
This folder is reserved for the optional exported Optimum Quanto qint8 LLM-component artifact.
Run:
```bash
python scripts/export_quanto_qint8_artifact.py quantized_artifacts
python scripts/test_quanto_qint8_artifact_reload.py quantized_artifacts
|