MycroftAI
/
mimic2
mirror of https://github.com/MycroftAI/mimic2.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Added check for wav file existence

pull/45/head
Thorsten Mueller 2020-01-21 18:10:19 +01:00
parent 34e8126763
commit 0a37404582
2 changed files with 13 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
datasets/createljspeech.py
View File

@ -31,10 +31,14 @@ def main():
metadata = open(os.path.join(dir_base_ljspeech,"metadata.csv"),mode="w", encoding="utf8")
for row in c.execute('SELECT audio_id, prompt, lower(prompt) FROM audiomodel ORDER BY length(prompt)'):
metadata.write(row[0] + "|" + row[1] + "|" + row[2] + "\n")
audio_file_source = os.path.join(dir_base_mrs,"backend","audio_files", uid, row[0] + ".wav")
audio_file_dest = os.path.join(dir_base_ljspeech_wav,row[0] + ".wav")
copyfile(audio_file_source,audio_file_dest)
if os.path.isfile(audio_file_source):
metadata.write(row[0] + "|" + row[1] + "|" + row[2] + "\n")
audio_file_dest = os.path.join(dir_base_ljspeech_wav,row[0] + ".wav")
copyfile(audio_file_source,audio_file_dest)
else:
print("File " + audio_file_source + " no found. Skipping.")
metadata.close()
conn.close()

9
datasets/mrs.py
View File

@ -44,9 +44,12 @@ def build_from_path(in_dir, out_dir, num_workers=1, tqdm=lambda x: x):
for row in c.execute('SELECT audio_id, lower(prompt) FROM audiomodel ORDER BY length(prompt)'):
wav_path = os.path.join(wav_dir, '%s.wav' % row[0])
text = row[1]
futures.append(executor.submit(partial(_process_utterance, out_dir, index, wav_path, text)))
index += 1
if os.path.isfile(wav_path):
text = row[1]
futures.append(executor.submit(partial(_process_utterance, out_dir, index, wav_path, text)))
index += 1
else:
print("File " + wav_path + " no found. Skipping.")
return [future.result() for future in tqdm(futures)]