Question: easier way to generate data for voice cloning [Project]

• diff-svc

  9 2,594 2.8 Jupyter Notebook

  Singing Voice Conversion via diffusion model

I'm new to voice cloning, but basically, I want to modify the the song Edelweiss from the sound of music and explore making an extended version with christopher plummer's voice (I know he didn't sing the recording in the movie). Anyway, I saw that for Sovits you need 3 hours of voice recordings in 5-15 second chunks to train a diff-SVC model. So I collected youtube recordings of interviews, and found someone on Fiverr who can do the editing, but she's gonna cost $250 to edit the videos into WAV files. Does anyone know an easier way to sort through video for audio clips and automatically cut them up?

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project