alakxender/voice-synthetic download history
alakxender/voice-synthetic is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 89 times (14 in the last 7 days), and 1,756 times in total. It ranks #165,100 among datasets by monthly downloads.
Voice Synthetic Dataset A Dhivehi text-to-speech dataset containing professionally recorded audio samples with their corresponding transcriptions. Dataset Configuration Audio Format: WAV files Language: Dhivehi (dv) Source: cv Split Ratio: Train: 80% Test: 20% Struc
Models trained on voice-synthetic
7 models list it as training data.
- alakxender/mms-tts-div-ft-spk01-f01 204 downloads in 30 days
- alakxender/csm-1b-dhivehi-5-spk-gd 73 downloads in 30 days
- alakxender/mms-tts-div-ft-spk01-m01 70 downloads in 30 days
- alakxender/csm-1b-dhivehi-2-speakers 14 downloads in 30 days
- alakxender/Dia-1.6B-dhivehi-ep1 8 downloads in 30 days
- alakxender/Dia-1.6B-dhivehi-18k 3 downloads in 30 days
- alakxender/moss-ttsd-dv-ft-t01 – downloads in 30 days
Open alakxender/voice-synthetic on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.