From 59f051a867ce29f1005a4de9764547775b74b2ca Mon Sep 17 00:00:00 2001 From: TianYuan Date: Fri, 10 Dec 2021 15:49:11 +0800 Subject: [PATCH 01/10] Update README.md --- demos/text_to_speech/README.md | 39 ++++++++++++++++++++++++++-------- 1 file changed, 30 insertions(+), 9 deletions(-) diff --git a/demos/text_to_speech/README.md b/demos/text_to_speech/README.md index 9751adf2..caa372ed 100644 --- a/demos/text_to_speech/README.md +++ b/demos/text_to_speech/README.md @@ -1,3 +1,4 @@ + # TTS(Text To Speech) ## Introduction @@ -13,15 +14,35 @@ pip install paddlespeech ### 2. Prepare Input Input of this demo should be a text of the specific language that can be passed via argument. - - ### 3. Usage -- Command Line(Recommended) - ```bash - paddlespeech tts --input 今天的天气不错啊 - ``` - Usage: - ```bash +- Command Line (Recommended) + - Chinese + ```bash + paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！" + ``` + The default acoustic model is `Fastspeech2`, and the default vocoder is `Parallel WaveGAN`. + - Chinese, use `SpeedySpeech` as acoustic model + ```bash + paddlespeech tts --am speedyspeech_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！" + ``` + - Chinese, multi speaker + ```bash + paddlespeech tts --am fastspeech2_aishell3 --voc pwgan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0 + ``` + You can change `spk_id` here. + - English + ```bash + paddlespeech tts --am fastspeech2_ljspeech --voc pwgan_ljspeech --lang en --input "hello world" + ``` + - English, multi speaker + ```bash + paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "hello, boys" --lang en --spk_id 0 + ``` + You can change `spk_id` here. + + +- Usage: +```bash paddlespeech tts --help ``` Arguments: @@ -79,7 +100,7 @@ Input of this demo should be a text of the specific language that can be passed ``` -### 4.Pretrained Models +### 4. Pretrained Models Here is a list of pretrained models released by PaddleSpeech that can be used by command and python api: From 11a48901bac5c8a3df9506ba883cfcbd160af0ac Mon Sep 17 00:00:00 2001 From: TianYuan Date: Fri, 10 Dec 2021 15:51:17 +0800 Subject: [PATCH 02/10] Update README.md --- demos/text_to_speech/README.md | 36 +++++++++++++++++----------------- 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/demos/text_to_speech/README.md b/demos/text_to_speech/README.md index caa372ed..b8b75f83 100644 --- a/demos/text_to_speech/README.md +++ b/demos/text_to_speech/README.md @@ -19,26 +19,26 @@ Input of this demo should be a text of the specific language that can be passed - Chinese ```bash paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！" - ``` + ``` The default acoustic model is `Fastspeech2`, and the default vocoder is `Parallel WaveGAN`. - - Chinese, use `SpeedySpeech` as acoustic model + - Chinese, use `SpeedySpeech` as acoustic model ```bash - paddlespeech tts --am speedyspeech_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！" - ``` - - Chinese, multi speaker - ```bash - paddlespeech tts --am fastspeech2_aishell3 --voc pwgan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0 - ``` - You can change `spk_id` here. - - English - ```bash - paddlespeech tts --am fastspeech2_ljspeech --voc pwgan_ljspeech --lang en --input "hello world" - ``` - - English, multi speaker - ```bash - paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "hello, boys" --lang en --spk_id 0 - ``` - You can change `spk_id` here. + paddlespeech tts --am speedyspeech_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！" + ``` + - Chinese, multi speaker + ```bash + paddlespeech tts --am fastspeech2_aishell3 --voc pwgan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0 + ``` + You can change `spk_id` here. + - English + ```bash + paddlespeech tts --am fastspeech2_ljspeech --voc pwgan_ljspeech --lang en --input "hello world" + ``` + - English, multi speaker + ```bash + paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "hello, boys" --lang en --spk_id 0 + ``` + You can change `spk_id` here. - Usage: From 02b3b09987e5daf558c3a492c5146be14ead43ee Mon Sep 17 00:00:00 2001 From: TianYuan Date: Fri, 10 Dec 2021 15:53:40 +0800 Subject: [PATCH 03/10] Update README.md --- demos/text_to_speech/README.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/demos/text_to_speech/README.md b/demos/text_to_speech/README.md index b8b75f83..518f9adc 100644 --- a/demos/text_to_speech/README.md +++ b/demos/text_to_speech/README.md @@ -25,20 +25,20 @@ Input of this demo should be a text of the specific language that can be passed ```bash paddlespeech tts --am speedyspeech_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！" ``` - - Chinese, multi speaker + - Chinese, multi speaker ```bash paddlespeech tts --am fastspeech2_aishell3 --voc pwgan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0 ``` You can change `spk_id` here. - - English + - English ```bash paddlespeech tts --am fastspeech2_ljspeech --voc pwgan_ljspeech --lang en --input "hello world" ``` - English, multi speaker ```bash paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "hello, boys" --lang en --spk_id 0 - ``` - You can change `spk_id` here. + ``` + You can change `spk_id` here. - Usage: From 88a8ed4fc306588589e476fba8ee3460228c01aa Mon Sep 17 00:00:00 2001 From: TianYuan Date: Fri, 10 Dec 2021 15:54:05 +0800 Subject: [PATCH 04/10] Update README.md --- demos/text_to_speech/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/demos/text_to_speech/README.md b/demos/text_to_speech/README.md index 518f9adc..2474a900 100644 --- a/demos/text_to_speech/README.md +++ b/demos/text_to_speech/README.md @@ -1,5 +1,5 @@ -# TTS(Text To Speech) +# TTS (Text To Speech) ## Introduction Text-to-speech (TTS) is a natural language modeling process that requires changing units of text into units of speech for audio presentation. From a34a6b1d2071914fd737437f858caf2157b7af50 Mon Sep 17 00:00:00 2001 From: TianYuan Date: Fri, 10 Dec 2021 15:56:35 +0800 Subject: [PATCH 05/10] Update README.md --- demos/text_to_speech/README.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/demos/text_to_speech/README.md b/demos/text_to_speech/README.md index 2474a900..a07120e2 100644 --- a/demos/text_to_speech/README.md +++ b/demos/text_to_speech/README.md @@ -37,12 +37,12 @@ Input of this demo should be a text of the specific language that can be passed - English, multi speaker ```bash paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "hello, boys" --lang en --spk_id 0 - ``` + ``` You can change `spk_id` here. - -- Usage: -```bash + Usage: + + ```bash paddlespeech tts --help ``` Arguments: From f9672e16ae0523bdfc2ffff3565a80cf1ba73bbf Mon Sep 17 00:00:00 2001 From: TianYuan Date: Fri, 10 Dec 2021 15:57:40 +0800 Subject: [PATCH 06/10] Update README.md --- demos/text_to_speech/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/demos/text_to_speech/README.md b/demos/text_to_speech/README.md index a07120e2..a1198b4b 100644 --- a/demos/text_to_speech/README.md +++ b/demos/text_to_speech/README.md @@ -1,4 +1,5 @@ + # TTS (Text To Speech) ## Introduction @@ -39,8 +40,7 @@ Input of this demo should be a text of the specific language that can be passed paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "hello, boys" --lang en --spk_id 0 ``` You can change `spk_id` here. - - Usage: + Usage: ```bash paddlespeech tts --help From 689c44dc59c6ca3d6c1f444588081d0430ec89df Mon Sep 17 00:00:00 2001 From: TianYuan Date: Fri, 10 Dec 2021 16:03:09 +0800 Subject: [PATCH 07/10] Update README.md --- demos/text_to_speech/README.md | 44 +++++++++++++++++----------------- 1 file changed, 22 insertions(+), 22 deletions(-) diff --git a/demos/text_to_speech/README.md b/demos/text_to_speech/README.md index a1198b4b..f25dc606 100644 --- a/demos/text_to_speech/README.md +++ b/demos/text_to_speech/README.md @@ -17,29 +17,29 @@ pip install paddlespeech Input of this demo should be a text of the specific language that can be passed via argument. ### 3. Usage - Command Line (Recommended) - - Chinese - ```bash - paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！" - ``` - The default acoustic model is `Fastspeech2`, and the default vocoder is `Parallel WaveGAN`. - - Chinese, use `SpeedySpeech` as acoustic model - ```bash - paddlespeech tts --am speedyspeech_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！" - ``` - - Chinese, multi speaker - ```bash - paddlespeech tts --am fastspeech2_aishell3 --voc pwgan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0 - ``` - You can change `spk_id` here. + - Chinese + ```bash + paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！" + ``` + The default acoustic model is `Fastspeech2`, and the default vocoder is `Parallel WaveGAN`. + - Chinese, use `SpeedySpeech` as acoustic model + ```bash + paddlespeech tts --am speedyspeech_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！" + ``` + - Chinese, multi speaker + ```bash + paddlespeech tts --am fastspeech2_aishell3 --voc pwgan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0 + ``` + You can change `spk_id` here. - English - ```bash - paddlespeech tts --am fastspeech2_ljspeech --voc pwgan_ljspeech --lang en --input "hello world" - ``` - - English, multi speaker - ```bash - paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "hello, boys" --lang en --spk_id 0 - ``` - You can change `spk_id` here. + ```bash + paddlespeech tts --am fastspeech2_ljspeech --voc pwgan_ljspeech --lang en --input "hello world" + ``` + - English, multi speaker + ```bash + paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "hello, boys" --lang en --spk_id 0 + ``` + You can change `spk_id` here. Usage: ```bash From d97379d7cea6ebc5ee07981554f91d6026f99c77 Mon Sep 17 00:00:00 2001 From: TianYuan Date: Fri, 10 Dec 2021 16:11:14 +0800 Subject: [PATCH 08/10] Update README.md --- demos/text_to_speech/README.md | 44 ++++++++++++++++++---------------- 1 file changed, 23 insertions(+), 21 deletions(-) diff --git a/demos/text_to_speech/README.md b/demos/text_to_speech/README.md index f25dc606..769189e3 100644 --- a/demos/text_to_speech/README.md +++ b/demos/text_to_speech/README.md @@ -1,5 +1,3 @@ - - # TTS (Text To Speech) ## Introduction @@ -18,29 +16,33 @@ Input of this demo should be a text of the specific language that can be passed ### 3. Usage - Command Line (Recommended) - Chinese - ```bash - paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！" - ``` - The default acoustic model is `Fastspeech2`, and the default vocoder is `Parallel WaveGAN`. - - Chinese, use `SpeedySpeech` as acoustic model - ```bash - paddlespeech tts --am speedyspeech_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！" - ``` + + The default acoustic model is `Fastspeech2`, and the default vocoder is `Parallel WaveGAN`. + ```bash + paddlespeech tts --input "你好，欢迎使用百度飞桨深度学习框架！" + ``` + - Chinese, use `SpeedySpeech` as acoustic model + ```bash + paddlespeech tts --am speedyspeech_csmsc --input "你好，欢迎使用百度飞桨深度学习框架！" + ``` - Chinese, multi speaker - ```bash - paddlespeech tts --am fastspeech2_aishell3 --voc pwgan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0 - ``` - You can change `spk_id` here. + + You can change `spk_id` here. + ```bash + paddlespeech tts --am fastspeech2_aishell3 --voc pwgan_aishell3 --input "你好，欢迎使用百度飞桨深度学习框架！" --spk_id 0 + ``` + - English - ```bash - paddlespeech tts --am fastspeech2_ljspeech --voc pwgan_ljspeech --lang en --input "hello world" - ``` + ```bash + paddlespeech tts --am fastspeech2_ljspeech --voc pwgan_ljspeech --lang en --input "hello world" + ``` - English, multi speaker - ```bash + + You can change `spk_id` here. + ```bash paddlespeech tts --am fastspeech2_vctk --voc pwgan_vctk --input "hello, boys" --lang en --spk_id 0 - ``` - You can change `spk_id` here. - Usage: + ``` + Usage: ```bash paddlespeech tts --help From b8d8fdccd6997723072c55b4b1d5cbc02a574676 Mon Sep 17 00:00:00 2001 From: TianYuan Date: Fri, 10 Dec 2021 16:22:33 +0800 Subject: [PATCH 09/10] Update quick_start.md --- docs/source/tts/quick_start.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/tts/quick_start.md b/docs/source/tts/quick_start.md index e6ad46fb..64c13bdf 100644 --- a/docs/source/tts/quick_start.md +++ b/docs/source/tts/quick_start.md @@ -19,7 +19,7 @@ The models in PaddleSpeech TTS have the following mapping relationship: ## Quick Start -Let's take a FastSpeech2 + Parallel WaveGAN with CSMSC dataset for instance. (./examples/csmsc/)(https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc) +Let's take a FastSpeech2 + Parallel WaveGAN with CSMSC dataset for instance. [./examples/csmsc/](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc) ### Train Parallel WaveGAN with CSMSC - Go to directory From 094d05f6b8c54007b24a87fc8d1d6d6cd9444d78 Mon Sep 17 00:00:00 2001 From: TianYuan Date: Fri, 10 Dec 2021 16:23:04 +0800 Subject: [PATCH 10/10] Update quick_start.md --- docs/source/tts/quick_start.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/tts/quick_start.md b/docs/source/tts/quick_start.md index 64c13bdf..a50f0a8b 100644 --- a/docs/source/tts/quick_start.md +++ b/docs/source/tts/quick_start.md @@ -19,7 +19,7 @@ The models in PaddleSpeech TTS have the following mapping relationship: ## Quick Start -Let's take a FastSpeech2 + Parallel WaveGAN with CSMSC dataset for instance. [./examples/csmsc/](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc) +Let's take a FastSpeech2 + Parallel WaveGAN with CSMSC dataset for instance. [examples/csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc) ### Train Parallel WaveGAN with CSMSC - Go to directory