This repository contains the CSV files for the processed dataset used to train VoiceLDM. These files include the transcriptions generated using the Whisper model.

• as_speech_en.csv
• cv1.csv (cv.csv has been split into two due to file size limitations on GitHub.)
• cv2.csv
• voxceleb.csv

• as_noise.csv
• noise_demand.csv

Additionally, I've included the CSV file corresponding to the ac_filtered test set, which was specifically used to evaluate VoiceLDM.

• ac_filtered.csv