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

Improve runtime of __parse_items() from O(|speakers|*|items|) to O(|items|)

This commit is contained in:
mueller 2020-09-16 15:09:02 +02:00
parent e732db76f1
commit d733b90255
1 changed files with 29 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
TTS/speaker_encoder/dataset.py
View File

@ -51,21 +51,37 @@ class MyDataset(Dataset):
return sample
def __parse_items(self):
"""
Find unique speaker ids and create a dict mapping utterances from speaker id
"""
speakers = list({item[-1] for item in self.items})
self.speaker_to_utters = {}
self.speakers = []
for speaker in speakers:
speaker_utters = [item[1] for item in self.items if item[2] == speaker]
if len(speaker_utters) < self.num_utter_per_speaker and self.skip_speakers:
print(
f" [!] Skipped speaker {speaker}. Not enough utterances {self.num_utter_per_speaker} vs {len(speaker_utters)}."
)
for i in self.items:
path_ = i[1]
speaker_ = i[2]
if speaker_ in self.speaker_to_utters.keys():
self.speaker_to_utters[speaker_].append(path_)
else:
self.speakers.append(speaker)
self.speaker_to_utters[speaker] = speaker_utters
self.speaker_to_utters[speaker_] = [path_, ]
if self.skip_speakers:
self.speaker_to_utters = {k: v for (k, v) in self.speaker_to_utters.items() if
len(v) >= self.num_utter_per_speaker}
self.speakers = [k for (k, v) in self.speaker_to_utters]
# def __parse_items(self):
# """
# Find unique speaker ids and create a dict mapping utterances from speaker id
# """
# speakers = list({item[-1] for item in self.items})
# self.speaker_to_utters = {}
# self.speakers = []
# for speaker in speakers:
# speaker_utters = [item[1] for item in self.items if item[2] == speaker]
# if len(speaker_utters) < self.num_utter_per_speaker and self.skip_speakers:
# print(
# f" [!] Skipped speaker {speaker}. Not enough utterances {self.num_utter_per_speaker} vs {len(speaker_utters)}."
# )
# else:
# self.speakers.append(speaker)
# self.speaker_to_utters[speaker] = speaker_utters
def __len__(self):
return int(1e10)