45d6f3b99d
specify a U(-.05, .05) initializer for Embedding
2020-10-30 17:42:06 +08:00
57d820f055
add support for channel last in batch_spec, and Conv1dBatchNorm
2020-10-30 15:13:57 +08:00
36cc543348
minor fixes to TransformerTTS
2020-10-28 11:05:47 +08:00
c43216ae9b
1. API renaming Conv1d -> Conv1D, BatchNorm1d -> BatchNorm1D;
...
2. add losses in parakeet/modules;
3. fix a bug in phonetics;
4. TransformerTTS update: encoder dim can be different from decoder dim;
5. MultiHeadAttention in TransformerTTS: add k_input_dim & v_input_dim in __init__ to allow differemt feature sizes for k and v.
2020-10-22 05:04:45 +00:00
c1e0aecdde
1. import models into parakeet.models;
...
2. add predict for TransformerTTS and test its io.
2020-10-16 13:51:56 +08:00
5270774bb0
tested io for TransformerTTS
2020-10-15 22:48:09 +08:00
40457227e6
move Conv1dBatchNorm to conv.py
2020-10-14 10:05:26 +08:00
f9087ea9a2
add masking functions
2020-10-13 15:53:18 +08:00
a8192c79cc
WIP: refactor
2020-10-10 15:51:54 +08:00
chenfeiyu