{"id":954,"slug":"espnet--yodas3","name":"yodas3","author":"espnet","description":"\n\t\n\t\t\n\t\n\t\n\t\tYODAS v3\n\t\n\nPaper\nYODAS v3 is a large web-crawled dataset containing over 1.1 million hours of audio that were originally released under a CC-BY-3.0 license. The dataset contains audio in over 100 languages. YODAS v3 can be used for a variety of multi-modal tasks, including Automatic Speech Recognition, Text-to-Speech, and Audio Representation Learning. We crawl a distinct set of videos from the v1 and v2 versions of YODAS, to guarantee that there are no overlaps in the data.\nFor… See the full description on the dataset page: https://huggingface.co/datasets/espnet/yodas3.","tags":"[\"Task_categories:audio-To-Audio\",\"Task_categories:automatic-Speech-Recognition\",\"Task_categories:text-To-Speech\",\"Task_categories:translation\",\"Size_categories:1M<n<10M\",\"Format:parquet\"]","license":null,"framework":null,"parameters":null,"downloads":95934,"likes":169,"verified":0,"created_at":"2026-10-03 13:23:29","updated_at":"2026-10-03 13:23:29","source_url":"https://huggingface.co/datasets/espnet/yodas3","source_platform":"huggingface","hf_repo_id":"espnet/yodas3","ollama_name":"","category":"dataset","latest_version":"v1.0.0","version_count":1,"signature_count":1,"risk_level":null,"risk_score":null,"versions":[{"id":953,"model_id":954,"version":"v1.0.0","manifest_hash":"e30950e2e95b3b4597ec97aa3aed49e2b2b786304ce21d1f337f6ac70eca1eaf","file_count":0,"total_size":0,"r2_manifest_key":"manifests/datasets/espnet--yodas3/v1.0.0.json","created_at":"2026-10-03 13:23:29"}],"files":[],"signatures":[{"id":1526,"version_id":953,"signer_did":"did:quantamrkt:registry:shield-v1","algorithm":"ML-DSA-65","signature_hex":"6ab625921a2a1ad3d64fbf11cff16f91108ab23be1a9b592b72ba859c318963a","attestation_type":"registry","signed_at":"2026-10-03 13:23:29"}],"hndl":null}