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

Merge pull request #573 from houqp/qp_voxceleb 

speed up metafile build for voxceleb
This commit is contained in:
Eren Gölge 2020-11-17 13:47:08 +01:00 committed by GitHub
parent a2a142dc39 b0b97d636f
commit 4f2201c143
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TTS/bin/train_encoder.py
View File

@ -35,7 +35,7 @@ print(" > Using CUDA: ", use_cuda)
print(" > Number of GPUs: ", num_gpus) print(" > Number of GPUs: ", num_gpus)
def setup_loader(ap, is_val=False, verbose=False): def setup_loader(ap: AudioProcessor, is_val: bool=False, verbose: bool=False):
if is_val: if is_val:
loader = None loader = None
else: else:

7
TTS/tts/datasets/preprocess.py
View File

@ -228,7 +228,6 @@ def brspeech(root_path, meta_file):
if line.startswith("wav_filename"): if line.startswith("wav_filename"):
continue continue
cols = line.split('|') cols = line.split('|')
#print(cols)
wav_file = os.path.join(root_path, cols[0]) wav_file = os.path.join(root_path, cols[0])
text = cols[2] text = cols[2]
speaker_name = cols[3] speaker_name = cols[3]
@ -304,17 +303,17 @@ def _voxcel_x(root_path, meta_file, voxcel_idx):
elif not cache_to.exists(): elif not cache_to.exists():
cnt = 0 cnt = 0
meta_data = "" meta_data = []
wav_files = voxceleb_path.rglob("**/*.wav") wav_files = voxceleb_path.rglob("**/*.wav")
for path in tqdm(wav_files, desc=f"Building VoxCeleb {voxcel_idx} Meta file ... this needs to be done only once.", for path in tqdm(wav_files, desc=f"Building VoxCeleb {voxcel_idx} Meta file ... this needs to be done only once.",
total=expected_count): total=expected_count):
speaker_id = str(Path(path).parent.parent.stem) speaker_id = str(Path(path).parent.parent.stem)
assert speaker_id.startswith('id') assert speaker_id.startswith('id')
text = None # VoxCel does not provide transciptions, and they are not needed for training the SE text = None # VoxCel does not provide transciptions, and they are not needed for training the SE
meta_data += f"{text}|{path}|voxcel{voxcel_idx}_{speaker_id}\n" meta_data.append(f"{text}|{path}|voxcel{voxcel_idx}_{speaker_id}\n")
cnt += 1 cnt += 1
with open(str(cache_to), 'w') as f: with open(str(cache_to), 'w') as f:
f.write(meta_data) f.write("".join(meta_data))
if cnt < expected_count: if cnt < expected_count:
raise ValueError(f"Found too few instances for Voxceleb. Should be around {expected_count}, is: {cnt}") raise ValueError(f"Found too few instances for Voxceleb. Should be around {expected_count}, is: {cnt}")