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

Make style

This commit is contained in:
Eren G??lge 2023-06-21 12:02:06 +02:00
parent 0f8932a6a9
commit 3b9fca2398
2 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -11,7 +11,7 @@ from TTS.utils.generic_utils import get_user_data_dir
@dataclass @dataclass
class BarkConfig(BaseTTSConfig): class BarkConfig(BaseTTSConfig):
""" Bark TTS configuration """Bark TTS configuration
Args: Args:
model (str): model name that registers the model. model (str): model name that registers the model.

12
TTS/tts/layers/bark/inference_funcs.py
View File

@ -49,11 +49,11 @@ def get_voices(extra_voice_dirs: List[str] = []):
def load_npz(npz_file): def load_npz(npz_file):
x_history = np.load(npz_file) x_history = np.load(npz_file)
semantic = x_history["semantic_prompt"] semantic = x_history["semantic_prompt"]
coarse = x_history["coarse_prompt"] coarse = x_history["coarse_prompt"]
fine = x_history["fine_prompt"] fine = x_history["fine_prompt"]
return semantic, coarse, fine return semantic, coarse, fine
def load_voice(model, voice: str, extra_voice_dirs: List[str] = []): # pylint: disable=dangerous-default-value def load_voice(model, voice: str, extra_voice_dirs: List[str] = []): # pylint: disable=dangerous-default-value
@ -79,9 +79,9 @@ def load_voice(model, voice: str, extra_voice_dirs: List[str] = []): # pylint:
# replace the file extension with .npz # replace the file extension with .npz
output_path = os.path.splitext(audio_path)[0] + ".npz" output_path = os.path.splitext(audio_path)[0] + ".npz"
generate_voice(audio=audio_path, model=model, output_path=output_path) generate_voice(audio=audio_path, model=model, output_path=output_path)
breakpoint()
return load_voice(model, voice, extra_voice_dirs) return load_voice(model, voice, extra_voice_dirs)
def zero_crossing_rate(audio, frame_length=1024, hop_length=512): def zero_crossing_rate(audio, frame_length=1024, hop_length=512):
zero_crossings = np.sum(np.abs(np.diff(np.sign(audio))) / 2) zero_crossings = np.sum(np.abs(np.diff(np.sign(audio))) / 2)
total_frames = 1 + int((len(audio) - frame_length) / hop_length) total_frames = 1 + int((len(audio) - frame_length) / hop_length)