deepgeek/Matcha-TTS
2
0
Fork 0
mirror of https://github.com/shivammehta25/Matcha-TTS.git synced 2026-02-04 09:49:21 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix a typo

Browse Source
This commit is contained in:
Jim O’Regan
2024-12-02 15:21:31 +01:00
committed by GitHub
parent 0735e653fc
commit 8e5f98476e
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
matcha/models/matcha_tts.py
View File

@@ -106,6 +106,7 @@ class MatchaTTS(BaseLightningClass): # 🍵
# Lengths of mel spectrograms # Lengths of mel spectrograms
"rtf": float, "rtf": float,
# Real-time factor # Real-time factor
}
""" """
# For RTF computation # For RTF computation
t = dt.datetime.now() t = dt.datetime.now()
@@ -152,7 +153,7 @@ class MatchaTTS(BaseLightningClass): # 🍵
def forward(self, x, x_lengths, y, y_lengths, spks=None, out_size=None, cond=None, durations=None): def forward(self, x, x_lengths, y, y_lengths, spks=None, out_size=None, cond=None, durations=None):
""" """
Computes 3 losses: Computes 3 losses:
1. duration loss: loss between predicted token durations and those extracted by Monotinic Alignment Search (MAS). 1. duration loss: loss between predicted token durations and those extracted by Monotonic Alignment Search (MAS).
2. prior loss: loss between mel-spectrogram and encoder outputs. 2. prior loss: loss between mel-spectrogram and encoder outputs.
3. flow matching loss: loss between mel-spectrogram and decoder outputs. 3. flow matching loss: loss between mel-spectrogram and decoder outputs.