Hi there!
Wanted to generate synthetic samples from audios of about 1 or 3 mins length. Would it be possible to generate such samples? The original audios contain speaker's speech. I see that for speech, you generated a sequence of numbers only, does this mean a limitation over continuous speech wav files generation?
Hi there! Wanted to generate synthetic samples from audios of about 1 or 3 mins length. Would it be possible to generate such samples? The original audios contain speaker's speech. I see that for speech, you generated a sequence of numbers only, does this mean a limitation over continuous speech wav files generation?