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

Uses mutagen for all audio formats

This commit is contained in:
Edresson Casanova 2023-11-07 10:36:14 -03:00
parent dc7624adb4
commit d551a597e0
1 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
TTS/tts/datasets/dataset.py
View File

@ -14,6 +14,8 @@ 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 from mutagen.mp3 import MP3
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
@ -48,13 +50,15 @@ def get_audio_size(audiopath):
extension = audiopath.rpartition(".")[-1].lower() extension = audiopath.rpartition(".")[-1].lower()
if extension == "mp3": if extension == "mp3":
audio_info = MP3(audiopath).info audio_info = MP3(audiopath).info
return int(audio_info.length * audio_info.sample_rate) elif extension == "wav":
if extension in ("wav", "flac"): audio_info = WAVE(audiopath).info
compress_factor = 8 elif extension == "flac":
bitrate = 16 # assuming 16bit audio audio_info = FLAC(audiopath).info
return int(os.path.getsize(audiopath) / bitrate * compress_factor) 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!")
return int(audio_info.length * audio_info.sample_rate)
class TTSDataset(Dataset): class TTSDataset(Dataset):
def __init__( def __init__(