diff --git a/README.md b/README.md index b5f61fd..aacf6c3 100644 --- a/README.md +++ b/README.md @@ -76,29 +76,61 @@ Entries to the introduction, and the launch of training and synthsis for differe Parakeet also releases some well-trained parameters for the example models, which can be accessed in the following tables. Each column of these tables lists resources for one model, including the url link to the pre-trained model, the dataset that the model is trained on and the total training steps, and several synthesized audio samples based on the pre-trained model. -- Vocoders +#### Vocoders + +We provide the model checkpoints of WaveFlow with 64 and 128 residual channels, ClariNet and WaveNet.
- - + + + + + + + + + + + + + + + + + +
- WaveFlow + WaveFlow (res. channels 64) - ClariNet + WaveFlow (res. channels 128)
LJSpeech, 2MLJSpeech, 500KLJSpeech, 3020 KLJSpeech
+ +
+ +
+ +
+ +
+ + + 		To be added soon
+ ClariNet + + WaveNet +
LJSpeech, 500 KLJSpeech, 2450 K

@@ -111,15 +143,57 @@ Parakeet also releases some well-trained parameters for the example models, whic 		+ +
+ +
+ +
+ +
+ + +
-    **Note:** The input mel spectrogams are from validation dataset, which are not seen during training. +      **Note:** The input mel spectrogams are from validation dataset, which are not seen during training. -- TTS models +#### TTS models + +
+ + + + + + + + + + + + + + + + + + +
+ Deep Voice 3 + + Transformer TTS +
LJSpeech LJSpeech
+ To be added soon + + To be added soon +
+
Click each link to download, then you can get the compressed package which contains the pre-trained model and the `yaml` config describing how to train the model.