msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity

Merge pull request #1949 from yt605155624/aishell3_doc

Browse Source 
[doc]update readme, test=doc
pull/1953/head
TianYuan 2 years ago committed by GitHub
parent 5ee3cc0c31 7a88e3f4e4
commit 657c424f6c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
23 changed files with 31 additions and 74 deletions
Show Stats Download Patch File Download Diff File

11
examples/aishell3/tts3/README.md
Unescape View File

@ -6,15 +6,8 @@ AISHELL-3 is a large-scale and high-fidelity multi-speaker Mandarin speech corpu
We use AISHELL-3 to train a multi-speaker fastspeech2 model here.
## Dataset
### Download and Extract
Download AISHELL-3.
```bash
wget https://www.openslr.org/resources/93/data_aishell3.tgz
```
Extract AISHELL-3.
```bash
mkdir data_aishell3
tar zxvf data_aishell3.tgz -C data_aishell3
```
Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishell_3) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/data_aishell3`.
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for aishell3_fastspeech2.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.

11
examples/aishell3/vc0/README.md
Unescape View File

@ -6,15 +6,8 @@ This example contains code used to train a [Tacotron2](https://arxiv.org/abs/171
## Dataset
### Download and Extract
Download AISHELL-3.
```bash
wget https://www.openslr.org/resources/93/data_aishell3.tgz
```
Extract AISHELL-3.
```bash
mkdir data_aishell3
tar zxvf data_aishell3.tgz -C data_aishell3
```
Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishell_3) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/data_aishell3`.
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get phonemes for Tacotron2, the durations of MFA are not needed here.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.

11
examples/aishell3/vc1/README.md
Unescape View File

@ -6,15 +6,8 @@ This example contains code used to train a [FastSpeech2](https://arxiv.org/abs/2
## Dataset
### Download and Extract
Download AISHELL-3.
```bash
wget https://www.openslr.org/resources/93/data_aishell3.tgz
```
Extract AISHELL-3.
```bash
mkdir data_aishell3
tar zxvf data_aishell3.tgz -C data_aishell3
```
Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishell_3) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/data_aishell3`.
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for aishell3_fastspeech2.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.

11
examples/aishell3/voc1/README.md
Unescape View File

@ -4,15 +4,8 @@ This example contains code used to train a [parallel wavegan](http://arxiv.org/a
AISHELL-3 is a large-scale and high-fidelity multi-speaker Mandarin speech corpus that could be used to train multi-speaker Text-to-Speech (TTS) systems.
## Dataset
### Download and Extract
Download AISHELL-3.
```bash
wget https://www.openslr.org/resources/93/data_aishell3.tgz
```
Extract AISHELL-3.
```bash
mkdir data_aishell3
tar zxvf data_aishell3.tgz -C data_aishell3
```
Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishell_3) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/data_aishell3`.
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for aishell3_fastspeech2.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.

10
examples/aishell3/voc5/README.md
Unescape View File

@ -4,15 +4,7 @@ This example contains code used to train a [HiFiGAN](https://arxiv.org/abs/2010.
AISHELL-3 is a large-scale and high-fidelity multi-speaker Mandarin speech corpus that could be used to train multi-speaker Text-to-Speech (TTS) systems.
## Dataset
### Download and Extract
Download AISHELL-3.
```bash
wget https://www.openslr.org/resources/93/data_aishell3.tgz
```
Extract AISHELL-3.
```bash
mkdir data_aishell3
tar zxvf data_aishell3.tgz -C data_aishell3
```
Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishell_3) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/data_aishell3`.
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for aishell3_fastspeech2.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.

2
examples/csmsc/tts0/README.md
Unescape View File

@ -3,7 +3,7 @@ This example contains code used to train a [Tacotron2](https://arxiv.org/abs/171
## Dataset
### Download and Extract
Download CSMSC from it's [Official Website](https://test.data-baker.com/data/index/source).
Download CSMSC from it's [Official Website](https://test.data-baker.com/data/index/TNtts/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get phonemes for Tacotron2, the durations of MFA are not needed here.

2
examples/csmsc/tts2/README.md
Unescape View File

@ -3,7 +3,7 @@ This example contains code used to train a [SpeedySpeech](http://arxiv.org/abs/2
## Dataset
### Download and Extract
Download CSMSC from it's [Official Website](https://test.data-baker.com/data/index/source).
Download CSMSC from it's [Official Website](https://test.data-baker.com/data/index/TNtts/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for SPEEDYSPEECH.

2
examples/csmsc/tts3/README.md
Unescape View File

@ -4,7 +4,7 @@ This example contains code used to train a [Fastspeech2](https://arxiv.org/abs/2
## Dataset
### Download and Extract
Download CSMSC from it's [Official Website](https://test.data-baker.com/data/index/source).
Download CSMSC from it's [Official Website](https://test.data-baker.com/data/index/TNtts/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for fastspeech2.

2
examples/csmsc/tts3/README_cn.md
Unescape View File

@ -5,7 +5,7 @@
## 数据集
### 下载并解压
从 [官方网站](https://test.data-baker.com/data/index/source) 下载数据集
从 [官方网站](https://test.data-baker.com/data/index/TNtts/) 下载数据集
### 获取MFA结果并解压
我们使用 [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) 去获得 fastspeech2 的音素持续时间。

2
examples/csmsc/voc1/README.md
Unescape View File

@ -2,7 +2,7 @@
This example contains code used to train a [parallel wavegan](http://arxiv.org/abs/1910.11480) model with [Chinese Standard Mandarin Speech Copus](https://www.data-baker.com/open_source.html).
## Dataset
### Download and Extract
Download CSMSC from the [official website](https://www.data-baker.com/data/index/source) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
Download CSMSC from it's [official website](https://test.data-baker.com/data/index/TNtts/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut silence at the edge of audio.

2
examples/csmsc/voc3/README.md
Unescape View File

@ -2,7 +2,7 @@
This example contains code used to train a [Multi Band MelGAN](https://arxiv.org/abs/2005.05106) model with [Chinese Standard Mandarin Speech Copus](https://www.data-baker.com/open_source.html).
## Dataset
### Download and Extract
Download CSMSC from the [official website](https://www.data-baker.com/data/index/source) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
Download CSMSC from it's [official website](https://test.data-baker.com/data/index/TNtts/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut the silence in the edge of audio.

2
examples/csmsc/voc4/README.md
Unescape View File

@ -2,7 +2,7 @@
This example contains code used to train a [Style MelGAN](https://arxiv.org/abs/2011.01557) model with [Chinese Standard Mandarin Speech Copus](https://www.data-baker.com/open_source.html).
## Dataset
### Download and Extract
Download CSMSC from the [official website](https://www.data-baker.com/data/index/source) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
Download CSMSC from it's [official website](https://test.data-baker.com/data/index/TNtts/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut the silence in the edge of audio.

2
examples/csmsc/voc5/README.md
Unescape View File

@ -2,7 +2,7 @@
This example contains code used to train a [HiFiGAN](https://arxiv.org/abs/2010.05646) model with [Chinese Standard Mandarin Speech Copus](https://www.data-baker.com/open_source.html).
## Dataset
### Download and Extract
Download CSMSC from the [official website](https://www.data-baker.com/data/index/source) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
Download CSMSC from it's [official website](https://test.data-baker.com/data/index/TNtts/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut silence at the edge of audio.

2
examples/csmsc/voc6/README.md
Unescape View File

@ -2,7 +2,7 @@
This example contains code used to train a [WaveRNN](https://arxiv.org/abs/1802.08435) model with [Chinese Standard Mandarin Speech Copus](https://www.data-baker.com/open_source.html).
## Dataset
### Download and Extract
Download CSMSC from the [official website](https://www.data-baker.com/data/index/source) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
Download CSMSC from it's [official website](https://test.data-baker.com/data/index/TNtts/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/BZNSYP`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut silence at the edge of audio.

2
examples/ljspeech/tts0/README.md
Unescape View File

@ -3,7 +3,7 @@ This example contains code used to train a [Tacotron2](https://arxiv.org/abs/171
## Dataset
### Download and Extract
Download LJSpeech-1.1 from the [official website](https://keithito.com/LJ-Speech-Dataset/).
Download LJSpeech-1.1 from it's [Official Website](https://keithito.com/LJ-Speech-Dataset/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/LJSpeech-1.1`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get phonemes for Tacotron2, the durations of MFA are not needed here.

11
examples/ljspeech/tts1/README.md
Unescape View File

@ -1,13 +1,10 @@
# TransformerTTS with LJSpeech
## Dataset
We experiment with the LJSpeech dataset. Download and unzip [LJSpeech](https://keithito.com/LJ-Speech-Dataset/).
```bash
wget https://data.keithito.com/data/speech/LJSpeech-1.1.tar.bz2
tar xjvf LJSpeech-1.1.tar.bz2
```
### Download and Extract
Download LJSpeech-1.1 from it's [Official Website](https://keithito.com/LJ-Speech-Dataset/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/LJSpeech-1.1`.
## Get Started
Assume the path to the dataset is `~/datasets/LJSpeech-1.1`.
Assume the path to the dataset is `~/datasets/LJSpeech-1.1` and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/LJSpeech-1.1`.
Run the command below to
1. **source path**.
2. preprocess the dataset.

2
examples/ljspeech/tts3/README.md
Unescape View File

@ -3,7 +3,7 @@ This example contains code used to train a [Fastspeech2](https://arxiv.org/abs/2
## Dataset
### Download and Extract
Download LJSpeech-1.1 from the [official website](https://keithito.com/LJ-Speech-Dataset/).
Download LJSpeech-1.1 from it's [Official Website](https://keithito.com/LJ-Speech-Dataset/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/LJSpeech-1.1`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for fastspeech2.

8
examples/ljspeech/voc0/README.md
Unescape View File

@ -1,11 +1,7 @@
# WaveFlow with LJSpeech
## Dataset
We experiment with the LJSpeech dataset. Download and unzip [LJSpeech](https://keithito.com/LJ-Speech-Dataset/).
```bash
wget https://data.keithito.com/data/speech/LJSpeech-1.1.tar.bz2
tar xjvf LJSpeech-1.1.tar.bz2
```
### Download and Extract
Download LJSpeech-1.1 from it's [Official Website](https://keithito.com/LJ-Speech-Dataset/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/LJSpeech-1.1`.
## Get Started
Assume the path to the dataset is `~/datasets/LJSpeech-1.1`.
Assume the path to the Tacotron2 generated mels is `../tts0/output/test`.

2
examples/ljspeech/voc1/README.md
Unescape View File

@ -2,7 +2,7 @@
This example contains code used to train a [parallel wavegan](http://arxiv.org/abs/1910.11480) model with [LJSpeech-1.1](https://keithito.com/LJ-Speech-Dataset/).
## Dataset
### Download and Extract
Download LJSpeech-1.1 from the [official website](https://keithito.com/LJ-Speech-Dataset/).
Download LJSpeech-1.1 from it's [Official Website](https://keithito.com/LJ-Speech-Dataset/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/LJSpeech-1.1`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut the silence in the edge of audio.
You can download from here [ljspeech_alignment.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/LJSpeech-1.1/ljspeech_alignment.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.

2
examples/ljspeech/voc5/README.md
Unescape View File

@ -2,7 +2,7 @@
This example contains code used to train a [HiFiGAN](https://arxiv.org/abs/2010.05646) model with [LJSpeech-1.1](https://keithito.com/LJ-Speech-Dataset/).
## Dataset
### Download and Extract
Download LJSpeech-1.1 from the [official website](https://keithito.com/LJ-Speech-Dataset/).
Download LJSpeech-1.1 from it's [Official Website](https://keithito.com/LJ-Speech-Dataset/) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/LJSpeech-1.1`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut the silence in the edge of audio.
You can download from here [ljspeech_alignment.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/LJSpeech-1.1/ljspeech_alignment.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.

2
examples/vctk/tts3/README.md
Unescape View File

@ -3,7 +3,7 @@ This example contains code used to train a [Fastspeech2](https://arxiv.org/abs/2
## Dataset
### Download and Extract the dataset
Download VCTK-0.92 from the [official website](https://datashare.ed.ac.uk/handle/10283/3443).
Download VCTK-0.92 from it's [Official Website](https://datashare.ed.ac.uk/handle/10283/3443) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/VCTK-Corpus-0.92`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for fastspeech2.

2
examples/vctk/voc1/README.md
Unescape View File

@ -3,7 +3,7 @@ This example contains code used to train a [parallel wavegan](http://arxiv.org/a
## Dataset
### Download and Extract
Download VCTK-0.92 from the [official website](https://datashare.ed.ac.uk/handle/10283/3443) and extract it to `~/datasets`. Then the dataset is in directory `~/datasets/VCTK-Corpus-0.92`.
Download VCTK-0.92 from it's [Official Website](https://datashare.ed.ac.uk/handle/10283/3443) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/VCTK-Corpus-0.92`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut the silence in the edge of audio.

2
examples/vctk/voc5/README.md
Unescape View File

@ -3,7 +3,7 @@ This example contains code used to train a [HiFiGAN](https://arxiv.org/abs/2010.
## Dataset
### Download and Extract
Download VCTK-0.92 from the [official website](https://datashare.ed.ac.uk/handle/10283/3443) and extract it to `~/datasets`. Then the dataset is in directory `~/datasets/VCTK-Corpus-0.92`.
Download VCTK-0.92 from it's [Official Website](https://datashare.ed.ac.uk/handle/10283/3443) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/VCTK-Corpus-0.92`.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut the silence in the edge of audio.

Write Preview
Loading…
Cancel
Save