Created
April 17, 2020 03:58
-
-
Save Iamgoofball/a1a5d54bc2dbcdcef83335607d4d3cd6 to your computer and use it in GitHub Desktop.
/mlp/ datasets -> tacotron standard, make sure to pip install pysoundfile, numpy, and pprint
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import io | |
| import glob, os | |
| import pprint | |
| import soundfile | |
| def main(): | |
| file_object = open('compiled_dataset.txt', 'a') | |
| os.mkdir("processed_audio") | |
| line_count = 0 | |
| for filename in glob.iglob('./**', recursive=True): | |
| if os.path.isfile(filename) and os.path.splitext(filename)[1] == ".flac": # filter dirs | |
| line_count += 1 | |
| print(os.path.splitext(filename)[0]) | |
| print(os.path.splitext(filename)[1]) | |
| transcription = open(os.path.splitext(filename)[0] + ".txt") | |
| print(os.path.basename(filename)) | |
| voiceline_transcription = transcription.read() | |
| print(voiceline_transcription) | |
| data, samplerate = soundfile.read(filename) | |
| soundfile.write("./processed_audio/line_"+str(line_count)+".wav", data, 48000, subtype="PCM_16") | |
| if voiceline_transcription: | |
| file_object.write("wavs/out/line_"+str(line_count)+".wav"+"|"+voiceline_transcription+"\n") | |
| else: | |
| print("No transcription made for this file!") | |
| file_object.close() | |
| if __name__ == "__main__": | |
| main() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment