add cnndecoder pretrained model, test=doc

78219cef · 小湉湉 · 4d7cd0e0 · 78219cef
隐藏空白更改
内联并排

Showing with 1 addition and 0 deletion

examples/csmsc/tts3/README.md examples/csmsc/tts3/README.md +1 -0

未找到文件。
--- a/examples/csmsc/tts3/README.md
+++ b/examples/csmsc/tts3/README.md
@@ -226,6 +226,7 @@ CUDA_VISIBLE_DEVICES=${gpus} ./local/inference.sh ${train_output_path}
 Pretrained FastSpeech2 model with no silence in the edge of audios:
 - [fastspeech2_nosil_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_nosil_baker_ckpt_0.4.zip)
 - [fastspeech2_conformer_baker_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_conformer_baker_ckpt_0.5.zip)
+- [fastspeech2_cnndecoder_csmsc_ckpt_1.0.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_cnndecoder_csmsc_ckpt_1.0.0.zip)

 The static model can be downloaded here:
 - [fastspeech2_nosil_baker_static_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_nosil_baker_static_0.4.zip)