Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Use mutagen.File

This commit is contained in:
Edresson Casanova 2023-11-08 08:36:17 -03:00
parent 775a81838c
commit 87bb01a42b
1 changed files with 3 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
TTS/tts/datasets/dataset.py
View File

@ -13,9 +13,7 @@ from TTS.tts.utils.data import prepare_data, prepare_stop_target, prepare_tensor
from TTS.utils.audio import AudioProcessor from TTS.utils.audio import AudioProcessor
from TTS.utils.audio.numpy_transforms import compute_energy as calculate_energy from TTS.utils.audio.numpy_transforms import compute_energy as calculate_energy
from mutagen.mp3 import MP3 import mutagen
from mutagen.flac import FLAC
from mutagen.wave import WAVE
# to prevent too many open files error as suggested here # to prevent too many open files error as suggested here
# https://github.com/pytorch/pytorch/issues/11201#issuecomment-421146936 # https://github.com/pytorch/pytorch/issues/11201#issuecomment-421146936
@ -48,15 +46,10 @@ def string2filename(string):
def get_audio_size(audiopath): def get_audio_size(audiopath):
extension = audiopath.rpartition(".")[-1].lower() extension = audiopath.rpartition(".")[-1].lower()
if extension == "mp3": if extension not in {"mp3", "wav", "flac"}:
audio_info = MP3(audiopath).info
elif extension == "wav":
audio_info = WAVE(audiopath).info
elif extension == "flac":
audio_info = FLAC(audiopath).info
else:
raise RuntimeError(f"The audio format {extension} is not supported, please convert the audio files for mp3, flac or wav format!") raise RuntimeError(f"The audio format {extension} is not supported, please convert the audio files for mp3, flac or wav format!")
audio_info = mutagen.File(audiopath).info
return int(audio_info.length * audio_info.sample_rate) return int(audio_info.length * audio_info.sample_rate)