Text-to-Audio
Transformers
Safetensors
qwen3_omni_moe
rasst
speech-translation
streaming-translation
research-artifact
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM
processor = AutoProcessor.from_pretrained("gavinlaw/rasst-speech-llm-ja-cap16-denoise-ttag")
model = AutoModelForMultimodalLM.from_pretrained("gavinlaw/rasst-speech-llm-ja-cap16-denoise-ttag", device_map="auto")Quick Links
gavinlaw/rasst-speech-llm-ja-cap16-denoise-ttag
Public RASST release artifact used by the global-cache 30/30/20/20 main result.
- Manifest asset key:
model_ja_cap16_denoise - Artifact type:
hf_model_dir - Original release source path:
/mnt/taurus/data1/jiaxuanluo/slm_local_cache/ja_tagged_acl_20260525/cap16_denoise_ttag/v2-20260525-235251-hf - Manifest metadata:
variant:cap16_denoise_ttag
This repository stores a Hugging Face-format Speech-LLM checkpoint directory.
See the RASST repository for manifests and launch wrappers: https://github.com/luojiaxuan/RASST
- Downloads last month
- 4
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="gavinlaw/rasst-speech-llm-ja-cap16-denoise-ttag")