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

Format style of the recipes

This commit is contained in:
Eren Gölge 2021-07-22 14:24:04 +02:00
parent 5d59100a88
commit 42862f7fdb
3 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TTS/tts/utils/measures.py
View File

@ -7,7 +7,7 @@ def alignment_diagonal_score(alignments, binary=False):
binary (bool): if True, ignore scores and consider attention binary (bool): if True, ignore scores and consider attention
as a binary mask. as a binary mask.
Shape: Shape:
alignments : batch x decoder_steps x encoder_steps - alignments : :math:`[B, T_de, T_en]`
""" """
maxs = alignments.max(dim=1)[0] maxs = alignments.max(dim=1)[0]
if binary: if binary:

1
TTS/utils/audio.py
View File

@ -693,7 +693,6 @@ class AudioProcessor(object):
# # plt.figure() # # plt.figure()
# plt.imshow(spec, aspect="auto", origin="lower") # plt.imshow(spec, aspect="auto", origin="lower")
# plt.savefig('save_img2.png') # plt.savefig('save_img2.png')
# breakpoint()
return f0 return f0
### Audio Processing ### ### Audio Processing ###

7
recipes/ljspeech/fast_pitch/train_fast_pitch.py
View File

@ -8,7 +8,12 @@ from TTS.utils.manage import ModelManager
output_path = os.path.dirname(os.path.abspath(__file__)) output_path = os.path.dirname(os.path.abspath(__file__))
# init configs # init configs
dataset_config = BaseDatasetConfig(name="ljspeech", meta_file_train="metadata.csv", meta_file_attn_mask=os.path.join(output_path, "../LJSpeech-1.1/metadata_attn_mask.txt"), path=os.path.join(output_path, "../LJSpeech-1.1/")) dataset_config = BaseDatasetConfig(
name="ljspeech",
meta_file_train="metadata.csv",
meta_file_attn_mask=os.path.join(output_path, "../LJSpeech-1.1/metadata_attn_mask.txt"),
path=os.path.join(output_path, "../LJSpeech-1.1/"),
)
audio_config = BaseAudioConfig( audio_config = BaseAudioConfig(
sample_rate=22050, sample_rate=22050,
do_trim_silence=False, do_trim_silence=False,