Skip to content

D
DeepSpeech

PaddlePaddle / DeepSpeech
大约 2 年 前同步成功

通知 210
Star 8425
Fork 1598
D
DeepSpeech
未验证 提交 ed8802bd 编写于 作者: H Hui Zhang 提交者： GitHub
浏览文件
操作

Merge pull request #956 from yt605155624/fix_docs 

[TTS]add tts demo in read the docs
上级 782b0ddc 15beee6e
隐藏空白更改
内联 并排
Showing with 977 addition and 119 deletion
README.md
浏览文件 @ ed8802bd
...@@ -74,9 +74,9 @@ Just a quick test of our functions: [English ASR](link/hubdetail?name=deepspeech ...@@ -74,9 +74,9 @@ Just a quick test of our functions: [English ASR](link/hubdetail?name=deepspeech
Developers can have a try of our model with only a few lines of code. Developers can have a try of our model with only a few lines of code.
A tiny *ASR* DeepSpeech2 model training on toy set of LibriSpeech: A tiny **ASR** DeepSpeech2 model training on toy set of LibriSpeech:
```shell ```bash
cd examples/tiny/s0/ cd examples/tiny/s0/
# source the environment # source the environment
source path.sh source path.sh
...@@ -86,16 +86,34 @@ bash local/data.sh ...@@ -86,16 +86,34 @@ bash local/data.sh
bash local/test.sh conf/deepspeech2.yaml ckptfile offline bash local/test.sh conf/deepspeech2.yaml ckptfile offline
``` ```
For *TTS*, try FastSpeech2 on LJSpeech: For **TTS**, try pretrained FastSpeech2 + Parallel WaveGAN on CSMSC:
- Download LJSpeech-1.1 from the [ljspeech official website](https://keithito.com/LJ-Speech-Dataset/), our prepared durations for fastspeech2 [ljspeech_alignment](https://paddlespeech.bj.bcebos.com/MFA/LJSpeech-1.1/ljspeech_alignment.tar.gz).
- The pretrained models are seperated into two parts: [fastspeech2_nosil_ljspeech_ckpt](https://paddlespeech.bj.bcebos.com/Parakeet/fastspeech2_nosil_ljspeech_ckpt_0.5.zip) and [pwg_ljspeech_ckpt](https://paddlespeech.bj.bcebos.com/Parakeet/pwg_ljspeech_ckpt_0.5.zip). Please download then unzip to `./model/fastspeech2` and `./model/pwg` respectively.
- Assume your path to the dataset is `~/datasets/LJSpeech-1.1` and `./ljspeech_alignment` accordingly, preprocess your data and then use our pretrained model to synthesize:
```shell
bash ./local/preprocess.sh conf/default.yaml
bash ./local/synthesize_e2e.sh conf/default.yaml ./model/fastspeech2/snapshot_iter_100000.pdz ./model/pwg/pwg_snapshot_iter_400000.pdz
```
```bash
cd examples/csmsc/tts3
# download the pretrained models and unaip them
wget https://paddlespeech.bj.bcebos.com/Parakeet/pwg_baker_ckpt_0.4.zip
unzip pwg_baker_ckpt_0.4.zip
wget https://paddlespeech.bj.bcebos.com/Parakeet/fastspeech2_nosil_baker_ckpt_0.4.zip
unzip fastspeech2_nosil_baker_ckpt_0.4.zip
# source the environment
source path.sh
# run end-to-end synthesize
FLAGS_allocator_strategy=naive_best_fit \
FLAGS_fraction_of_gpu_memory_to_use=0.01 \
python3 ${BIN_DIR}/synthesize_e2e.py \
--fastspeech2-config=fastspeech2_nosil_baker_ckpt_0.4/default.yaml \
--fastspeech2-checkpoint=fastspeech2_nosil_baker_ckpt_0.4/snapshot_iter_76000.pdz \
--fastspeech2-stat=fastspeech2_nosil_baker_ckpt_0.4/speech_stats.npy \
--pwg-config=pwg_baker_ckpt_0.4/pwg_default.yaml \
--pwg-checkpoint=pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz \
--pwg-stat=pwg_baker_ckpt_0.4/pwg_stats.npy \
--text=${BIN_DIR}/../sentences.txt \
--output-dir=exp/default/test_e2e \
--inference-dir=exp/default/inference \
--device="gpu" \
--phones-dict=fastspeech2_nosil_baker_ckpt_0.4/phone_id_map.txt
```
If you want to try more functions like training and tuning, please see [ASR getting started](docs/source/asr/getting_started.md) and [TTS Basic Use](/docs/source/tts/basic_usage.md). If you want to try more functions like training and tuning, please see [ASR getting started](docs/source/asr/getting_started.md) and [TTS Basic Use](/docs/source/tts/basic_usage.md).
......
docs/source/_static/custom.css 0 → 100644
浏览文件 @ ed8802bd
.wy-nav-content {
max-width: 80%;
}
.table table{ background:#b9b9b9}
.table table td{ background:#FFF; }
docs/source/conf.py
浏览文件 @ ed8802bd
...@@ -79,6 +79,9 @@ smartquotes = False ...@@ -79,6 +79,9 @@ smartquotes = False
# so a file named "default.css" will overwrite the builtin "default.css". # so a file named "default.css" will overwrite the builtin "default.css".
html_static_path = ['_static'] html_static_path = ['_static']
html_logo = '../images/paddle.png' html_logo = '../images/paddle.png'
html_css_files = [
'custom.css',
]
# -- Extension configuration ------------------------------------------------- # -- Extension configuration -------------------------------------------------
# numpydoc_show_class_members = False # numpydoc_show_class_members = False
docs/source/tts/demo.rst
浏览文件 @ ed8802bd
...@@ -27,74 +27,106 @@ Analysis/synthesis ...@@ -27,74 +27,106 @@ Analysis/synthesis
Audio samples generated from ground-truth spectrograms with a vocoder. Audio samples generated from ground-truth spectrograms with a vocoder.
.. raw:: html .. raw:: html
<b>LJSpeech(English)</b> <b>LJSpeech(English)</b>
<br> <br>
</br> </br>
<table>
<div class="table">
<table border="2" cellspacing="1" cellpadding="1">
<tr> <tr>
<th align="left"> GT </th> <th align="center"> Text </th>
<th align="left"> WaveFlow </th> <th align="center"> GT </th>
<th align="center"> WaveFlow </th>
</tr> </tr>
<tr> <tr>
<td >Printing, in the only sense with which we are at present concerned, differs from most if not from all the arts and crafts represented in the Exhibition</td>
<td> <td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/ljspeech_gt/LJ001-0001.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/ljspeech_gt/LJ001-0001.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/ljspeech_gt/LJ001-0002.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/waveflow_res128_ljspeech_samples_1.0/step_2000k_sentence_0.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>in being comparatively modern.</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/ljspeech_gt/LJ001-0003.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/ljspeech_gt/LJ001-0002.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
<audio controls="controls">
</td>
<td>
<audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/ljspeech_gt/LJ001-0004.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/waveflow_res128_ljspeech_samples_1.0/step_2000k_sentence_1.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>For although the Chinese took impressions from wood blocks engraved in relief for centuries before the woodcutters of the Netherlands, by a similar process</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/ljspeech_gt/LJ001-0005.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/ljspeech_gt/LJ001-0003.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td> </td>
<td> <td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/waveflow_res128_ljspeech_samples_1.0/step_2000k_sentence_0.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/waveflow_res128_ljspeech_samples_1.0/step_2000k_sentence_2.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>produced the block books, which were the immediate predecessors of the true printed book</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/waveflow_res128_ljspeech_samples_1.0/step_2000k_sentence_1.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/ljspeech_gt/LJ001-0004.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/waveflow_res128_ljspeech_samples_1.0/step_2000k_sentence_2.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/waveflow_res128_ljspeech_samples_1.0/step_2000k_sentence_3.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>the invention of movable metal letters in the middle of the fifteenth century may justly be considered as the invention of the art of printing.</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/waveflow_res128_ljspeech_samples_1.0/step_2000k_sentence_3.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/ljspeech_gt/LJ001-0005.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/waveflow_res128_ljspeech_samples_1.0/step_2000k_sentence_4.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/waveflow_res128_ljspeech_samples_1.0/step_2000k_sentence_4.wav"
...@@ -107,151 +139,468 @@ Audio samples generated from ground-truth spectrograms with a vocoder. ...@@ -107,151 +139,468 @@ Audio samples generated from ground-truth spectrograms with a vocoder.
<br> <br>
</br> </br>
<b>CSMSC(Chinese)</b> <b>CSMSC(Chinese)</b>
<br> <br>
</br> </br>
<table> <table border="2" cellspacing="1" cellpadding="1">
<tr> <tr>
<th align="left"> GT (convert to 24k) </th> <th align="center"> Text </th>
<th align="left"> ParallelWaveGAN </th> <th align="center"> GT (convert to 24k) </th>
<th align="center"> ParallelWaveGAN </th>
</tr> </tr>
<tr> <tr>
<td> <td>昨日，这名“伤者”与医生全部被警方依法刑事拘留</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/baker_gt_24k/009901.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/baker_gt_24k/009901.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/pwg_baker_ckpt_0.4/009901.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>钱伟长想到上海来办学校是经过深思熟虑的。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/baker_gt_24k/009902.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/baker_gt_24k/009902.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/pwg_baker_ckpt_0.4/009902.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>她见我一进门就骂，吃饭时也骂，骂得我抬不起头。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/baker_gt_24k/009903.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/baker_gt_24k/009903.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/pwg_baker_ckpt_0.4/009903.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>李述德在离开之前，只说了一句“柱驼杀父亲了”</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/baker_gt_24k/009904.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/baker_gt_24k/009904.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/baker_gt_24k/009905.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/pwg_baker_ckpt_0.4/009904.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td> </td>
</tr>
<tr>
<td>这种车票和保险单捆绑出售属于重复性购买。</td>
<td> <td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/pwg_baker_ckpt_0.4/009901.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/baker_gt_24k/009905.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/pwg_baker_ckpt_0.4/009902.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/pwg_baker_ckpt_0.4/009905.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
</table>
</div>
<br>
<br>
TTS
-------------------
Audio samples generated by a TTS system. Text is first transformed into spectrogram by a text-to-spectrogram model, then the spectrogram is converted into raw audio by a vocoder.
.. raw:: html
<b>LJSpeech(English)</b>
<br>
</br>
<div class="table">
<table border="2" cellspacing="1" cellpadding="1">
<tr>
<th align="center"> Text </th>
<th align="center"> TransformerTTS + WaveFlow </th>
<th align="center"> Tacotron2 + WaveFlow </th>
</tr>
<tr>
<td>Life was like a box of chocolates, you never know what you're gonna get.</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/001.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_1.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>With great power there must come great responsibility.</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/002.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/pwg_baker_ckpt_0.4/009903.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_2.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>To be or not to be, that’s a question.</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/003.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_3.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>A man can be destroyed but not defeated.</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/pwg_baker_ckpt_0.4/009904.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/004.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_4.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>Do not, for one repulse, give up the purpose that you resolved to effort.</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/pwg_baker_ckpt_0.4/009905.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/005.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_5.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td> </td>
</tr> </tr>
<tr>
</table> <td>Death is just a part of life, something we're all destined to do.</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/006.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_6.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>I think it's hard winning a war with words. </td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/007.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
TTS <td>
------------------- <audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_7.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>Don’t argue with the people of strong determination, because they may change the fact!</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/008.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
Audio samples generated by a TTS system. Text is first transformed into spectrogram by a text-to-spectrogram model, then the spectrogram is converted into raw audio by a vocoder. <td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_8.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>Love you three thousand times.</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/009.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
.. raw:: html <td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_9.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
</table>
<br>
</br>
<table> <b>CSMSC(Chinese)</b>
<br>
</br>
<table border="2" cellspacing="1" cellpadding="1">
<tr> <tr>
<th align="left"> TransformerTTS + WaveFlow </th> <th align="center"> Text </th>
<th align="left"> Tacotron2 + WaveFlow </th> <th align="center"> SpeedySpeech + ParallelWaveGAN </th>
<th align="center"> FastSpeech2 + ParallelWaveGAN </th>
</tr> </tr>
<tr> <tr>
<td>凯莫瑞安联合体的经济崩溃，迫在眉睫。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/001.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/001.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>对于所有想要离开那片废土，去寻找更美好生活的人来说。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/002.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/002.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>克哈，是你们所有人安全的港湾。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/003.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/003.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>为了保护尤摩扬人民不受异虫的残害，我所做的，比他们自己的领导委员会都多。</td>
<td> <td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/001.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/004.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/002.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/004.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>无论他们如何诽谤我，我将继续为所有泰伦人的最大利益，而努力奋斗。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/003.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/005.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/004.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/005.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>身为你们的元首，我带领泰伦人实现了人类统治领地和经济的扩张。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/005.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/006.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/006.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/006.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>我们将继续成长，用行动回击那些只会说风凉话，不愿意和我们相向而行的害群之马。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/007.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/007.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/008.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/007.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>帝国武装力量，无数的优秀儿女，正时刻守卫着我们的家园大门，但是他们孤木难支。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/transformer_tts_ljspeech_ckpt_0.4_waveflow_ljspeech_ckpt_0.3/009.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/008.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
...@@ -259,183 +608,289 @@ Audio samples generated by a TTS system. Text is first transformed into spectrog ...@@ -259,183 +608,289 @@ Audio samples generated by a TTS system. Text is first transformed into spectrog
<td> <td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_1.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/008.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>凡是今天应征入伍者，所获的所有刑罚罪责，减半。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_2.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/009.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_3.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/009.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
</table>
</div>
<br>
<br>
Multi-Speaker TTS
-------------------
PaddleSpeech also support Multi-Speaker TTS, we provide the audio demos generated by FastSpeech2 + ParallelWaveGAN, we use AISHELL-3 Multi-Speaker TTS dataset.
.. raw:: html
<div class="table">
<table border="2" cellspacing="1" cellpadding="1">
<tr>
<th align="center"> Text </th>
<th align="center"> Origin </th>
<th align="center"> Generated </th>
</tr>
<table>
<div>
<br>
<br>
Duration control in FastSpeech2
--------------------------------------
In our FastSpeech2, we can control ``duration``, ``pitch`` and ``energy``, we provide the audio demos of duration control here. ``duration`` means the duration of phonemes, when we reduce duration, the speed of audios will increase, and when we incerase ``duration``, the speed of audios will reduce.
The ``duration`` of different phonemes in a sentence can have different scale ratios (when you want to slow down one word and keep the other words' speed in a sentence). Here we use a fixed scale ratio for different phonemes to control the ``speed`` of audios.
The duration control in FastSpeech2 can control the speed of audios will keep the pitch. (in some speech tool, increase the speed will increase the pitch, and vice versa.)
.. raw:: html
<div class="table">
<table border="2" cellspacing="1" cellpadding="1">
<tr>
<th align="center"> Speed(0.8x) </th>
<th align="center"> Speed(1x) </th>
<th align="center"> Speed(1.2x) </th>
</tr>
<tr>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_4.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x0.8_001.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_5.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1_001.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_6.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1.2_001.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_7.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x0.8_002.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_8.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1_002.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/tacotron2_ljspeech_waveflow_samples_0.2/sentence_9.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1.2_002.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td> </td>
</tr> </tr>
</table>
<table>
<tr>
<th align="left"> SpeedySpeech + ParallelWaveGAN </th>
<th align="left"> FastSpeech2 + ParallelWaveGAN </th>
</tr>
<tr> <tr>
<td> <td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/001.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x0.8_003.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/002.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1_003.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/003.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1.2_003.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/004.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x0.8_004.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/005.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1_004.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/006.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1.2_004.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/007.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x0.8_005.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/008.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1_005.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speedyspeech_baker_ckpt_0.4_pwg_baker_ckpt_0.4/009.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1.2_005.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td> </td>
<td> </tr>
<tr>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/001.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x0.8_007.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/002.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1_007.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/003.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1.2_007.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/004.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x0.8_008.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/005.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1_008.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/006.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1.2_008.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/007.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x0.8_009.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/008.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1_009.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/fastspeech2_nosil_baker_ckpt_0.4_parallel_wavegan_baker_ckpt_0.4/009.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/speed/x1.2_009.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td> </td>
</tr> </tr>
</table>
<table>
<div>
<br>
<br>
Chinese TTS with/without text frontend Chinese TTS with/without text frontend
...@@ -447,12 +902,15 @@ We use ``FastSpeech2`` + ``ParallelWaveGAN`` here. ...@@ -447,12 +902,15 @@ We use ``FastSpeech2`` + ``ParallelWaveGAN`` here.
.. raw:: html .. raw:: html
<table> <div class="table">
<table border="2" cellspacing="1" cellpadding="1">
<tr> <tr>
<th align="left"> With Text Frontend </th> <th align="center"> Text</th>
<th align="left"> Without Text Frontend </th> <th align="center"> With Text Frontend </th>
<th align="center"> Without Text Frontend </th>
</tr> </tr>
<tr> <tr>
<td>他只是一个纸老虎。</td>
<td> <td>
<audio controls="controls"> <audio controls="controls">
<source <source
...@@ -460,116 +918,179 @@ We use ``FastSpeech2`` + ``ParallelWaveGAN`` here. ...@@ -460,116 +918,179 @@ We use ``FastSpeech2`` + ``ParallelWaveGAN`` here.
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/002.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/001.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>手表厂有五种好产品。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/003.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/002.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/004.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/002.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>老板的轿车需要保养。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/005.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/003.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/006.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/003.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>我们所有人都好喜欢你呀。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/007.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/004.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/008.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/004.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>岂有此理。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/009.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/005.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/010.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/005.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td> </td>
</tr>
<tr>
<td>虎骨酒多少钱一瓶。</td>
<td> <td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/001.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/006.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/002.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/006.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>这件事情需要冷处理。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/003.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/007.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/004.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/007.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>这个老奶奶是个大喇叭。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/005.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/008.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/006.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/008.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>我喜欢说相声。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/007.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/009.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/008.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/009.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
</tr>
<tr>
<td>有一天，我路过了一栋楼。</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/009.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/with_frontend/010.wav"
type="audio/wav"> type="audio/wav">
Your browser does not support the <code>audio</code> element. Your browser does not support the <code>audio</code> element.
</audio> </audio>
</td>
<td>
<audio controls="controls"> <audio controls="controls">
<source <source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/010.wav" src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/without_frontend/010.wav"
...@@ -579,5 +1100,9 @@ We use ``FastSpeech2`` + ``ParallelWaveGAN`` here. ...@@ -579,5 +1100,9 @@ We use ``FastSpeech2`` + ``ParallelWaveGAN`` here.
</td> </td>
</tr> </tr>
<table>
</div>
<br>
<br>
<table>
\ No newline at end of file \ No newline at end of file
docs/source/tts/demo_2.rst
浏览文件 @ ed8802bd
...@@ -5,3 +5,283 @@ This is an audio demo page to contrast PaddleSpeech TTS and Espnet TTS, We use t ...@@ -5,3 +5,283 @@ This is an audio demo page to contrast PaddleSpeech TTS and Espnet TTS, We use t
We use Espnet's released models here. We use Espnet's released models here.
FastSpeech2 + Parallel WaveGAN in CSMSC FastSpeech2 + Parallel WaveGAN in CSMSC
.. raw:: html
<div class="table">
<table border="2" cellspacing="1" cellpadding="1">
<tr>
<th align="center"> Text </th>
<th align="center"> Espent TTS </th>
<th align="center"> PaddleSpeech TTS </th>
</tr>
<tr>
<td>早上好，今天是2020/10/29，最低温度是-3°C。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/001.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/001.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>你好，我的编号是37249，很高兴为您服务。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/002.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/002.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>我们公司有37249个人。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/003.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/003.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>我出生于2005年10月8日。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/004.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/004.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>我们习惯在12:30吃中午饭。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/005.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/005.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>只要有超过3/4的人投票同意，你就会成为我们的新班长。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/006.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/006.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>我要买一只价值999.9元的手表。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/007.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/007.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>我的手机号是18544139121，欢迎来电。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/008.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/008.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>明天有62%的概率降雨。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/009.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/009.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>手表厂有五种好产品。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/010.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/010.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>跑马场有五百匹很勇敢的千里马。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/011.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/011.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>有一天，我看到了一栋楼，我顿感不妙，因为我看不清里面有没有人。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/012.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/012.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>史小姐拿着小雨伞去找她的老保姆了。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/013.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/013.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
<tr>
<td>不要相信这个老奶奶说的话，她一点儿也不好。</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/espent/014.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
<td>
<audio controls="controls">
<source
src="https://paddlespeech.bj.bcebos.com/Parakeet/docs/demos/parakeet_espnet_fs2_pwg_demo/tn_g2p/parakeet/014.wav"
type="audio/wav">
Your browser does not support the <code>audio</code> element.
</audio>
</td>
</tr>
</table>
</div>
docs/source/tts/test_sentence.txt 0 → 100644
浏览文件 @ ed8802bd
001 早上好，今天是2020/10/29，最低温度是-3°C。
002 你好，我的编号是37249，很高兴为您服务。
003 我们公司有37249个人。
004 我出生于2005年10月8日。
005 我们习惯在12:30吃中午饭。
006 只要有超过3/4的人投票同意，你就会成为我们的新班长。
007 我要买一只价值999.9元的手表。
008 我的手机号是18544139121，欢迎来电。
009 明天有62%的概率降雨。
010 手表厂有五种好产品。
011 跑马场有五百匹很勇敢的千里马。
012 有一天，我看到了一栋楼，我顿感不妙，因为我看不清里面有没有人。
013 史小姐拿着小雨伞去找她的老保姆了。
014 不要相信这个老奶奶说的话，她一点儿也不好。
\ No newline at end of file
parakeet/models/fastspeech2/fastspeech2.py
浏览文件 @ ed8802bd
...@@ -419,9 +419,18 @@ class FastSpeech2(nn.Layer): ...@@ -419,9 +419,18 @@ class FastSpeech2(nn.Layer):
if is_inference: if is_inference:
# (B, Tmax) # (B, Tmax)
d_outs = self.duration_predictor.inference(hs, d_masks) if ds is not None:
d_outs = ds
else:
d_outs = self.duration_predictor.inference(hs, d_masks)
if ps is not None:
p_outs = ps
if es is not None:
e_outs = es
# use prediction in inference # use prediction in inference
# (B, Tmax, 1) # (B, Tmax, 1)
p_embs = self.pitch_embed(p_outs.transpose((0, 2, 1))).transpose( p_embs = self.pitch_embed(p_outs.transpose((0, 2, 1))).transpose(
(0, 2, 1)) (0, 2, 1))
e_embs = self.energy_embed(e_outs.transpose((0, 2, 1))).transpose( e_embs = self.energy_embed(e_outs.transpose((0, 2, 1))).transpose(
...@@ -516,7 +525,7 @@ class FastSpeech2(nn.Layer): ...@@ -516,7 +525,7 @@ class FastSpeech2(nn.Layer):
x = paddle.cast(text, 'int64') x = paddle.cast(text, 'int64')
y = speech y = speech
spemb = spembs spemb = spembs
if durations: if durations is not None:
d = paddle.cast(durations, 'int64') d = paddle.cast(durations, 'int64')
p, e = pitch, energy p, e = pitch, energy
# setup batch axis # setup batch axis
...@@ -534,9 +543,12 @@ class FastSpeech2(nn.Layer): ...@@ -534,9 +543,12 @@ class FastSpeech2(nn.Layer):
if use_teacher_forcing: if use_teacher_forcing:
# use groundtruth of duration, pitch, and energy # use groundtruth of duration, pitch, and energy
ds, ps, es = d.unsqueeze(0), p.unsqueeze(0), e.unsqueeze(0) ds = d.unsqueeze(0) if d is not None else None
ps = p.unsqueeze(0) if p is not None else None
es = e.unsqueeze(0) if e is not None else None
# ds, ps, es = , p.unsqueeze(0), e.unsqueeze(0)
# (1, L, odim) # (1, L, odim)
_, outs, *_ = self._forward( _, outs, d_outs, *_ = self._forward(
xs, xs,
ilens, ilens,
ys, ys,
...@@ -545,10 +557,11 @@ class FastSpeech2(nn.Layer): ...@@ -545,10 +557,11 @@ class FastSpeech2(nn.Layer):
es=es, es=es,
spembs=spembs, spembs=spembs,
spk_id=spk_id, spk_id=spk_id,
tone_id=tone_id) tone_id=tone_id,
is_inference=True)
else: else:
# (1, L, odim) # (1, L, odim)
_, outs, *_ = self._forward( _, outs, d_outs, *_ = self._forward(
xs, xs,
ilens, ilens,
ys, ys,
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或