Skip to content

Commit 6873cfb

Browse files
r9y9r9y9
committed
update docs
1 parent 2061609 commit 6873cfb

File tree

2 files changed

+23
-12
lines changed

2 files changed

+23
-12
lines changed

‎docs/changelog.rst‎

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,12 @@
11
Change log
22
==========
33

4-
v0.2.1 <2021-xx-xx>
4+
v0.2.1 <2021-08-21>
55
-------------------
66

7+
- pretrained: add PWG TTS models for common voice (ja)
8+
- pretrained: add HiFi-GAN based TTS models using JVS and JSUT corpus
9+
- Add HiFi-GAN configs for JVS and JSUT extra recipes
710
- `#7`_: Add script to generate ground-truth aligned (GTA) features
811
- `#5`_: [docker] Push docker image to Docker Hub
912
- `#4`_: [docker] fix docker build fail because no 'gcc' command

‎docs/pretrained.rst‎

Lines changed: 19 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -30,17 +30,25 @@ Extra pretrained models
3030
Note that the following models are not explained in our book.
3131
Those were trained using extra recipes found in our GitHub repository.
3232

33-
+----------------------------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
34-
| Model ID | Class | Details of the model |
35-
+----------------------------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
36-
| ``tacotron2_pwg_jsut16k`` | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Tacotron 2 with Parallel WaveGAN (PWG). Trained on JSUT corpus. Sampling rate: 16 kHz. |
37-
+----------------------------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
38-
| ``tacotron2_pwg_jsut24k`` | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Tacotron 2 with Parallel WaveGAN (PWG). Trained on JSUT corpus. Sampling rate: 24 kHz. |
39-
+----------------------------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
40-
| ``multspk_tacotron2_pwg_jvs16k`` | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Multi-speaker Tacotron 2 with Parallel WaveGAN (PWG). Trained on JVS corpus. Sampling rate: 16 kHz. |
41-
+----------------------------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
42-
| ``multspk_tacotron2_pwg_jvs24k`` | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Multi-speaker Tacotron 2 with Parallel WaveGAN (PWG). Trained on JVS corpus. Sampling rate: 24 kHz. |
43-
+----------------------------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
33+
+--------------------------------------+--------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
34+
| Model ID | Corpus | Class | Details of the model |
35+
+--------------------------------------+--------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
36+
| ``tacotron2_pwg_jsut16k`` | JSUT | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Tacotron 2 with Parallel WaveGAN (PWG). Trained on JSUT corpus. Sampling rate: 16 kHz. |
37+
+--------------------------------------+--------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
38+
| ``tacotron2_pwg_jsut24k`` | JSUT | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Tacotron 2 with PWG. Trained on JSUT corpus. Sampling rate: 24 kHz. |
39+
+--------------------------------------+--------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
40+
| ``tacotron2_hifipwg_jsut24k`` | JSUT | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Tacotron 2 with HiFi-GAN. Trained on JSUT corpus. Sampling rate: 24 kHz. |
41+
+--------------------------------------+--------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
42+
| ``multspk_tacotron2_pwg_jvs16k`` | JVS | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Multi-speaker Tacotron 2 with PWG. Trained on JVS corpus. Sampling rate: 16 kHz. |
43+
+--------------------------------------+--------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
44+
| ``multspk_tacotron2_pwg_jvs24k`` | JVS | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Multi-speaker Tacotron 2 with Parallel WaveGAN (PWG). Trained on JVS corpus. Sampling rate: 24 kHz. |
45+
+--------------------------------------+--------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
46+
| ``multspk_tacotron2_hifipwg_jvs24k`` | JVS | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Multi-speaker Tacotron 2 with HiFi-GAN. Trained on JVS corpus. Sampling rate: 24 kHz. |
47+
+--------------------------------------+--------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
48+
| ``multspk_tacotron2_pwg_cv16k`` | common voice | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Multi-speaker Tacotron 2 with PWG. Trained on common voice (ja) corpus. Sampling rate: 16 kHz. |
49+
+--------------------------------------+--------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
50+
| ``multspk_tacotron2_pwg_cv24k`` | common voice | :py:class:`ttslearn.contrib.tacotron2_pwg.Tacotron2PWGTTS` | Multi-speaker Tacotron 2 with PWG. Trained on common voice (ja) corpus. Sampling rate: 24 kHz. |
51+
+--------------------------------------+--------------+------------------------------------------------------------+-----------------------------------------------------------------------------------------------------+
4452

4553
Helpers
4654
--------

0 commit comments

Comments
 (0)