deepgeek/Matcha-TTS
2
0
Fork 0
mirror of https://github.com/shivammehta25/Matcha-TTS.git synced 2026-02-05 02:09:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

Adding saving phones while getting durations from matcha

Browse Source
This commit is contained in:
Shivam Mehta
2024-03-02 12:47:08 +00:00
parent ad76016916
commit 294c6b1327
9 changed files with 126 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
matcha/data/text_mel_datamodule.py
View File

@@ -164,10 +164,10 @@ class TextMelDataset(torch.utils.data.Dataset):
filepath, text = filepath_and_text[0], filepath_and_text[1]
spk = None
text = self.get_text(text, add_blank=self.add_blank)
text, cleaned_text = self.get_text(text, add_blank=self.add_blank)
mel = self.get_mel(filepath)
return {"x": text, "y": mel, "spk": spk, "filepath": filepath}
return {"x": text, "y": mel, "spk": spk, "filepath": filepath, "x_text": cleaned_text}
def get_mel(self, filepath):
audio, sr = ta.load(filepath)
@@ -187,11 +187,11 @@ class TextMelDataset(torch.utils.data.Dataset):
return mel
def get_text(self, text, add_blank=True):
text_norm = text_to_sequence(text, self.cleaners)
text_norm, cleaned_text = text_to_sequence(text, self.cleaners)
if self.add_blank:
text_norm = intersperse(text_norm, 0)
text_norm = torch.IntTensor(text_norm)
return text_norm
return text_norm, cleaned_text
def __getitem__(self, index):
datapoint = self.get_datapoint(self.filepaths_and_text[index])
@@ -216,7 +216,7 @@ class TextMelBatchCollate:
x = torch.zeros((B, x_max_length), dtype=torch.long)
y_lengths, x_lengths = [], []
spks = []
filepaths = []
filepaths, x_texts = [], []
for i, item in enumerate(batch):
y_, x_ = item["y"], item["x"]
y_lengths.append(y_.shape[-1])
@@ -225,9 +225,18 @@ class TextMelBatchCollate:
x[i, : x_.shape[-1]] = x_
spks.append(item["spk"])
filepaths.append(item["filepath"])
x_texts.append(item["x_text"])
y_lengths = torch.tensor(y_lengths, dtype=torch.long)
x_lengths = torch.tensor(x_lengths, dtype=torch.long)
spks = torch.tensor(spks, dtype=torch.long) if self.n_spks > 1 else None
return {"x": x, "x_lengths": x_lengths, "y": y, "y_lengths": y_lengths, "spks": spks, "filepaths": filepaths}
return {
"x": x,
"x_lengths": x_lengths,
"y": y,
"y_lengths": y_lengths,
"spks": spks,
"filepaths": filepaths,
"x_texts": x_texts,
}