{"id":776,"slug":"sarulab-speech--yodas2_sidon","name":"yodas2_sidon","author":"sarulab-speech","description":"\n\t\n\t\t\n\t\tYODAS2-Sidon\n\t\n\n\n\t\n\t\t\n\t\tOverview\n\t\n\nThis dataset is a cleansed version of YODAS-2 with Sidon speech restoration mode for Speech Synthesis and Spoken Language Modeling.  \nYODAS-2 is a massive, multilingual YouTube-derived dataset. We have applied the Sidon restoration model to remove background noise and enhance audio quality, making it suitable for high-quality generation tasks.\nWe resampled original sidon output to 24kHz due to a storage constraints.\nThe dataset is provided in… See the full description on the dataset page: https://huggingface.co/datasets/sarulab-speech/yodas2_sidon.","tags":"[\"Task_categories:text-To-Speech\",\"Task_categories:automatic-Speech-Recognition\",\"Language:aa\",\"Language:ab\",\"Language:af\",\"Language:ak\"]","license":null,"framework":null,"parameters":null,"downloads":124991,"likes":64,"verified":0,"created_at":"2026-08-02 09:23:40","updated_at":"2026-08-02 09:23:40","source_url":"https://huggingface.co/datasets/sarulab-speech/yodas2_sidon","source_platform":"huggingface","hf_repo_id":"sarulab-speech/yodas2_sidon","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":775,"model_id":776,"version":"v1.0.0","manifest_hash":"bcf1199fec0e43f4074123afedf28837552d9921bea4446f24e2ad3bcf3edfbe","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/sarulab-speech--yodas2_sidon/v1.0.0.json","created_at":"2026-08-02 09:23:40"}],"files":[],"signatures":[{"id":1348,"version_id":775,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"d9645190bea11fc94315eae24f48829000811d8da88235ca35a433a0cc4292b0","attestation_type":"registry","signed_at":"2026-08-02 09:23:40"}],"hndl":null}