k9cli/video-vec2wav2-tokenizer download history
k9cli/video-vec2wav2-tokenizer is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 644,611 times (176,506 in the last 7 days), and 4,566,183 times in total. It ranks #23 among datasets by monthly downloads.
video-vec2wav2-tokenizer Production-ready pipeline (Python package video_vec2wav2_tokenizer, CLI command video2dataset) that turns a folder of videos into clean AI training datasets for speech recognition (ASR) and text-to-speech (TTS). videos ──► audio (16 kHz mono PCM) ──► whisp
Spaces using video-vec2wav2-tokenizer
- Model Pulse 8 likes