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

Fixups

This commit is contained in:
Eren G??lge 2023-06-26 12:55:18 +02:00
parent 115baf7e47
commit a1c431e6a9
5 changed files with 11 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TTS/tts/configs/fast_pitch_config.py
View File

@ -113,7 +113,7 @@ class FastPitchConfig(BaseTTSConfig):
base_model: str = "forward_tts" base_model: str = "forward_tts"
# model specific params # model specific params
model_args: ForwardTTSArgs = ForwardTTSArgs() model_args: ForwardTTSArgs = field(default_factory=ForwardTTSArgs)
# multi-speaker settings # multi-speaker settings
num_speakers: int = 0 num_speakers: int = 0

3
TTS/utils/audio/processor.py
View File

@ -540,7 +540,10 @@ class AudioProcessor(object):
def _griffin_lim(self, S): def _griffin_lim(self, S):
angles = np.exp(2j * np.pi * np.random.rand(*S.shape)) angles = np.exp(2j * np.pi * np.random.rand(*S.shape))
try:
S_complex = np.abs(S).astype(np.complex) S_complex = np.abs(S).astype(np.complex)
except AttributeError: # np.complex is deprecated since numpy 1.20.0
S_complex = np.abs(S).astype(complex)
y = self._istft(S_complex * angles) y = self._istft(S_complex * angles)
if not np.isfinite(y).all(): if not np.isfinite(y).all():
print(" [!] Waveform is not finite everywhere. Skipping the GL.") print(" [!] Waveform is not finite everywhere. Skipping the GL.")

1
TTS/utils/manage.py
View File

@ -287,6 +287,7 @@ class ModelManager(object):
"author": "fairseq", "author": "fairseq",
"description": "this model is released by Meta under Fairseq repo. Visit https://github.com/facebookresearch/fairseq/tree/main/examples/mms for more info.", "description": "this model is released by Meta under Fairseq repo. Visit https://github.com/facebookresearch/fairseq/tree/main/examples/mms for more info.",
} }
model_item["model_name"] = model_name
else: else:
# get model from models.json # get model from models.json
model_item = self.models_dict[model_type][lang][dataset][model] model_item = self.models_dict[model_type][lang][dataset][model]

4
TTS/vc/models/freevc.py
View File

@ -794,8 +794,8 @@ class FreeVCConfig(BaseVCConfig):
model: str = "freevc" model: str = "freevc"
# model specific params # model specific params
model_args: FreeVCArgs = FreeVCArgs() model_args: FreeVCArgs = field(default_factory=FreeVCArgs)
audio: FreeVCAudioConfig = FreeVCAudioConfig() audio: FreeVCAudioConfig = field(default_factory=FreeVCAudioConfig)
# optimizer # optimizer
# TODO with training support # TODO with training support

6
requirements.txt
View File

@ -1,6 +1,6 @@
# core deps # core deps
numpy==1.22.0 numpy==1.22.0;python_version<="3.10"
numpy==1.22.0 numpy==1.24.3;python_version>"3.10"
cython==0.29.30 cython==0.29.30
scipy>=1.4.0 scipy>=1.4.0
torch>=1.7 torch>=1.7
@ -8,7 +8,7 @@ torchaudio
soundfile soundfile
librosa==0.10.0.* librosa==0.10.0.*
numba==0.55.1;python_version<"3.9" numba==0.55.1;python_version<"3.9"
numba==0.56.4;python_version>="3.9" numba==0.57.0;python_version>="3.9"
inflect==5.6.0 inflect==5.6.0
tqdm tqdm
anyascii anyascii