testadmin
/
ParakeetRebeccaRosario
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

modified some vars name

This commit is contained in:
lifuchen 2020-03-06 02:47:16 +00:00
parent d08779d61e
commit 54bd759625
3 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
examples/fastspeech/README.md
View File

@ -1,5 +1,5 @@
# Fastspeech
Paddle fluid implementation of Fastspeech, a feed-forward network based on Transformer. The implementation is based on [FastSpeech: Fast, Robust and Controllable Text to Speech](https://arxiv.org/abs/1905.09263).
PaddlePaddle fluid implementation of Fastspeech, a feed-forward network based on Transformer. The implementation is based on [FastSpeech: Fast, Robust and Controllable Text to Speech](https://arxiv.org/abs/1905.09263).
## Dataset

8
examples/fastspeech/train.py
View File

@ -67,12 +67,12 @@ def main(args):
with dg.guard(place):
with fluid.unique_name.guard():
transformerTTS = TransformerTTS(cfg)
transformer_tts = TransformerTTS(cfg)
model_dict, _ = load_checkpoint(
str(args.transformer_step),
os.path.join(args.transtts_path, "transformer"))
transformerTTS.set_dict(model_dict)
transformerTTS.eval()
transformer_tts.set_dict(model_dict)
transformer_tts.eval()
model = FastSpeech(cfg)
model.train()
@ -105,7 +105,7 @@ def main(args):
mel_lens, enc_slf_mask, enc_query_mask, dec_slf_mask,
enc_dec_mask, dec_query_slf_mask, dec_query_mask) = data
_, _, attn_probs, _, _, _ = transformerTTS(
_, _, attn_probs, _, _, _ = transformer_tts(
character,
mel_input,
pos_text,

2
examples/transformer_tts/README.md
View File

@ -1,5 +1,5 @@
# TransformerTTS
PaddlePaddle fluid implementation of TransformerTTS, a neural TTS with Transformer. The implementation is based on [Neural Speech Synthesis with Transformer Network](https://arxiv.org/abs/1809.08895).
PaddlePaddle fluid implementation of TransformerTTS, a neural TTS model with Transformer. The implementation is based on [Neural Speech Synthesis with Transformer Network](https://arxiv.org/abs/1809.08895).
## Dataset