configname: default datafiles
Independent publisher
Yechanyu
dbdp961202
Models in Library0
Datasets in Library2
Models on Hugging Face—
Followers—
Compare the published evidence
This profile connects the 2 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text to speech.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Datasets
AI-generated multilingual speech using 1,124 synthetic English reference voices. Audio is mono 64kbps CBR Opus in approximately 1GB WebDataset tar shards. Source text: dbdp961202/emilia-translategemma-4b-55-locales (ttsaccepted). Reference voices: dbdp961202/voice-generator-reference-en. Model: openbmb/VoxCPM2. Original reference WAVs are not distributed here. Generation settings and speakermap.json are preserved in metadata/generations/. Audio and manifests are under data/ /part-xxxxx/; generation IDs remain in each sample metadata. Legacy task records are archived under metadata/legacytasks/. Verified legacy runs/ paths have been removed; production data uses the simplified data/ layout.…