diff --git a/examples/aishell3/tts3/README.md b/examples/aishell3/tts3/README.md index 130c52e1..c313d922 100644 --- a/examples/aishell3/tts3/README.md +++ b/examples/aishell3/tts3/README.md @@ -17,7 +17,7 @@ tar zxvf data_aishell3.tgz -C data_aishell3 ``` ### Get MFA result of AISHELL-3 and Extract it 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 own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/use_mfa) (use MFA1.x now) of our repo. +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 own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/other/use_mfa) (use MFA1.x now) of our repo. ## Get Started Assume the path to the dataset is `~/datasets/data_aishell3`. @@ -98,7 +98,7 @@ optional arguments: 7. `--speaker-dict`is the path of the speaker id map file when training a multi-speaker FastSpeech2. ### Synthesize -We use [parallel wavegan](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/parallelwave_gan/baker) as the neural vocoder. +We use [parallel wavegan](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/csmsc/voc1) as the neural vocoder. Download pretrained parallel wavegan model from [pwg_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/pwg_baker_ckpt_0.4.zip) and unzip it. ```bash unzip pwg_baker_ckpt_0.4.zip diff --git a/examples/aishell3/vc0/README.md b/examples/aishell3/vc0/README.md index d5803f64..9364cf00 100644 --- a/examples/aishell3/vc0/README.md +++ b/examples/aishell3/vc0/README.md @@ -1,8 +1,8 @@ # Tacotron2 + AISHELL-3 Voice Cloning This example contains code used to train a [Tacotron2 ](https://arxiv.org/abs/1712.05884) model with [AISHELL-3](http://www.aishelltech.com/aishell_3). The trained model can be used in Voice Cloning Task, We refer to the model structure of [Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](https://arxiv.org/pdf/1806.04558.pdf) . The general steps are as follows: -1. Speaker Encoder: We use a Speaker Verification to train a speaker encoder. Datasets used in this task are different from those used in Tacotron2, because the transcriptions are not needed, we use more datasets, refer to [ge2e](../../other/ge2e). +1. Speaker Encoder: We use a Speaker Verification to train a speaker encoder. Datasets used in this task are different from those used in Tacotron2, because the transcriptions are not needed, we use more datasets, refer to [ge2e](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/other/ge2e). 2. Synthesizer: Then, we use the trained speaker encoder to generate utterance embedding for each sentence in AISHELL-3. This embedding is a extra input of Tacotron2 which will be concated with encoder outputs. -3. Vocoder: We use WaveFlow as the neural Vocoder, refer to [waveflow](../../ljspeech/voc0). +3. Vocoder: We use WaveFlow as the neural Vocoder, refer to [waveflow](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/ljspeech/voc0). ## Get Started Assume the path to the dataset is `~/datasets/data_aishell3`. @@ -39,9 +39,9 @@ There are silence in the edge of AISHELL-3's wavs, and the audio amplitude is ve We use Montreal Force Aligner 1.0. The label in aishell3 include pinyin，so the lexicon we provided to MFA is pinyin rather than Chinese characters. And the prosody marks(`$` and `%`) need to be removed. You shoud preprocess the dataset into the format which MFA needs, the texts have the same name with wavs and have the suffix `.lab`. -We use [lexicon.txt](./lexicon.txt) as the lexicon. +We use [lexicon.txt](https://github.com/PaddlePaddle/DeepSpeech/blob/develop/parakeet/exps/voice_cloning/tacotron2_ge2e/lexicon.txt) as the lexicon. -You can download the alignment results from here [alignment_aishell3.tar.gz](https://paddlespeech.bj.bcebos.com/Parakeet/alignment_aishell3.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/use_mfa) (use MFA1.x now) of our repo. +You can download the alignment results from here [alignment_aishell3.tar.gz](https://paddlespeech.bj.bcebos.com/Parakeet/alignment_aishell3.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/other/use_mfa) (use MFA1.x now) of our repo. ```bash if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then diff --git a/examples/csmsc/tts2/README.md b/examples/csmsc/tts2/README.md index 4283e8cc..e73f81fa 100644 --- a/examples/csmsc/tts2/README.md +++ b/examples/csmsc/tts2/README.md @@ -7,7 +7,7 @@ Download CSMSC from it's [Official Website](https://test.data-baker.com/data/ind ### Get MFA result of CSMSC and Extract it We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for SPEEDYSPEECH. -You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/use_mfa) of our repo. +You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/other/use_mfa) of our repo. ## Get Started Assume the path to the dataset is `~/datasets/BZNSYP`. @@ -91,7 +91,7 @@ optional arguments: 7. `--tones-dict` is the path of the tone vocabulary file. ### Synthesize -We use [parallel wavegan](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/parallelwave_gan/baker) as the neural vocoder. +We use [parallel wavegan](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/csmsc/voc1) as the neural vocoder. Download pretrained parallel wavegan model from [pwg_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/pwg_baker_ckpt_0.4.zip) and unzip it. ```bash unzip pwg_baker_ckpt_0.4.zip diff --git a/examples/csmsc/tts3/README.md b/examples/csmsc/tts3/README.md index 735ef6d1..42f33faa 100644 --- a/examples/csmsc/tts3/README.md +++ b/examples/csmsc/tts3/README.md @@ -7,7 +7,7 @@ Download CSMSC from it's [Official Website](https://test.data-baker.com/data/ind ### Get MFA result of CSMSC and Extract it We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for fastspeech2. -You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/use_mfa) of our repo. +You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/other/use_mfa) of our repo. ## Get Started Assume the path to the dataset is `~/datasets/BZNSYP`. @@ -88,7 +88,7 @@ optional arguments: 6. `--phones-dict` is the path of the phone vocabulary file. ### Synthesize -We use [parallel wavegan](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/parallelwave_gan/baker) as the neural vocoder. +We use [parallel wavegan](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/csmsc/voc1) as the neural vocoder. Download pretrained parallel wavegan model from [pwg_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/pwg_baker_ckpt_0.4.zip) and unzip it. ```bash unzip pwg_baker_ckpt_0.4.zip diff --git a/examples/csmsc/voc1/README.md b/examples/csmsc/voc1/README.md index 2a7b3185..4b6b6c42 100644 --- a/examples/csmsc/voc1/README.md +++ b/examples/csmsc/voc1/README.md @@ -6,7 +6,7 @@ Download CSMSC from the [official website](https://www.data-baker.com/data/index ### Get MFA results for silence trim We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut silence in the edge of audio. -You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/use_mfa) of our repo. +You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/other/use_mfa) of our repo. ## Get Started Assume the path to the dataset is `~/datasets/BZNSYP`. diff --git a/examples/ljspeech/tts0/README.md b/examples/ljspeech/tts0/README.md index e95f6614..e8e3ebff 100644 --- a/examples/ljspeech/tts0/README.md +++ b/examples/ljspeech/tts0/README.md @@ -77,7 +77,7 @@ optional arguments: config, passing in KEY VALUE pairs -v, --verbose print msg ``` -**Ps.** You can use [waveflow](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/waveflow) as the neural vocoder to synthesize mels to wavs. (Please refer to `synthesize.sh` in our LJSpeech waveflow example) +**Ps.** You can use [waveflow](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/ljspeech/voc0) as the neural vocoder to synthesize mels to wavs. (Please refer to `synthesize.sh` in our LJSpeech waveflow example) ## Pretrained Models Pretrained Models can be downloaded from links below. We provide 2 models with different configurations. diff --git a/examples/ljspeech/tts1/README.md b/examples/ljspeech/tts1/README.md index 097dc08c..0385fdce 100644 --- a/examples/ljspeech/tts1/README.md +++ b/examples/ljspeech/tts1/README.md @@ -81,7 +81,7 @@ optional arguments: 6. `--phones-dict` is the path of the phone vocabulary file. ## Synthesize -We use [waveflow](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/waveflow) as the neural vocoder. +We use [waveflow](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/ljspeech/voc0) as the neural vocoder. Download Pretrained WaveFlow Model with residual channel equals 128 from [waveflow_ljspeech_ckpt_0.3.zip](https://paddlespeech.bj.bcebos.com/Parakeet/waveflow_ljspeech_ckpt_0.3.zip) and unzip it. ```bash unzip waveflow_ljspeech_ckpt_0.3.zip diff --git a/examples/ljspeech/tts3/README.md b/examples/ljspeech/tts3/README.md index f5bea6a9..dc711ce8 100644 --- a/examples/ljspeech/tts3/README.md +++ b/examples/ljspeech/tts3/README.md @@ -7,7 +7,7 @@ Download LJSpeech-1.1 from the [official website](https://keithito.com/LJ-Speech ### Get MFA result of LJSpeech-1.1 and Extract it We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for fastspeech2. -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 own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/use_mfa) of our repo. +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 own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/other/use_mfa) of our repo. ## Get Started Assume the path to the dataset is `~/datasets/LJSpeech-1.1`. @@ -88,7 +88,7 @@ optional arguments: 6. `--phones-dict` is the path of the phone vocabulary file. ### Synthesize -We use [parallel wavegan](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/parallelwave_gan/ljspeech/) as the neural vocoder. +We use [parallel wavegan](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/ljspeech/voc1) as the neural vocoder. Download pretrained parallel wavegan model from [pwg_ljspeech_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/pwg_ljspeech_ckpt_0.5.zip) and unzip it. ```bash unzip pwg_ljspeech_ckpt_0.5.zip diff --git a/examples/ljspeech/voc1/README.md b/examples/ljspeech/voc1/README.md index 995b4c7c..ba6eb002 100644 --- a/examples/ljspeech/voc1/README.md +++ b/examples/ljspeech/voc1/README.md @@ -5,7 +5,7 @@ This example contains code used to train a [parallel wavegan](http://arxiv.org/a Download LJSpeech-1.1 from the [official website](https://keithito.com/LJ-Speech-Dataset/). ### Get MFA results for silence trim We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut 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 own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/use_mfa) of our repo. +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 own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/other/use_mfa) of our repo. ## Get Started Assume the path to the dataset is `~/datasets/LJSpeech-1.1`. diff --git a/examples/other/ge2e/README.md b/examples/other/ge2e/README.md index 89365d63..1fa9677a 100644 --- a/examples/other/ge2e/README.md +++ b/examples/other/ge2e/README.md @@ -1,5 +1,5 @@ # Speaker Encoder -This experiment trains a speaker encoder with speaker verification as its task. It is done as a part of the experiment of transfer learning from speaker verification to multispeaker text-to-speech synthesis, which can be found at [tacotron2_aishell3](../tacotron2_shell3). The trained speaker encoder is used to extract utterance embeddings from utterances. +This experiment trains a speaker encoder with speaker verification as its task. It is done as a part of the experiment of transfer learning from speaker verification to multispeaker text-to-speech synthesis, which can be found at [examples/aishell3/vc0](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/aishell3/vc0). The trained speaker encoder is used to extract utterance embeddings from utterances. ## Model The model used in this experiment is the speaker encoder with text independent speaker verification task in [GENERALIZED END-TO-END LOSS FOR SPEAKER VERIFICATION](https://arxiv.org/pdf/1710.10467.pdf). GE2E-softmax loss is used. diff --git a/examples/vctk/tts3/README.md b/examples/vctk/tts3/README.md index 2a79cdd6..717ee7ac 100644 --- a/examples/vctk/tts3/README.md +++ b/examples/vctk/tts3/README.md @@ -7,8 +7,8 @@ Download VCTK-0.92 from the [official website](https://datashare.ed.ac.uk/handle ### Get MFA result of VCTK and Extract it We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for fastspeech2. -You can download from here [vctk_alignment.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/VCTK-Corpus-0.92/vctk_alignment.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/use_mfa) of our repo. -ps: we remove three speakers in VCTK-0.92 (see [reorganize_vctk.py](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/use_mfa/local/reorganize_vctk.py)): +You can download from here [vctk_alignment.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/VCTK-Corpus-0.92/vctk_alignment.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/other/use_mfa) of our repo. +ps: we remove three speakers in VCTK-0.92 (see [reorganize_vctk.py](https://github.com/PaddlePaddle/DeepSpeech/blob/develop/examples/other/use_mfa/local/reorganize_vctk.py)): 1. `p315`, because no txt for it. 2. `p280` and `p362`, because no *_mic2.flac (which is better than *_mic1.flac) for them. @@ -91,7 +91,7 @@ optional arguments: 6. `--phones-dict` is the path of the phone vocabulary file. ### Synthesize -We use [parallel wavegan](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/parallelwave_gan/baker) as the neural vocoder. +We use [parallel wavegan](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/vctk/voc1) as the neural vocoder. Download pretrained parallel wavegan model from [pwg_vctk_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/pwg_vctk_ckpt_0.5.zip)and unzip it. ```bash diff --git a/examples/vctk/voc1/README.md b/examples/vctk/voc1/README.md index b74b9d4a..cbfff32d 100644 --- a/examples/vctk/voc1/README.md +++ b/examples/vctk/voc1/README.md @@ -7,8 +7,8 @@ Download VCTK-0.92 from the [official website](https://datashare.ed.ac.uk/handl ### Get MFA results for silence trim We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut silence in the edge of audio. -You can download from here [vctk_alignment.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/VCTK-Corpus-0.92/vctk_alignment.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/use_mfa) of our repo. -ps: we remove three speakers in VCTK-0.92 (see [reorganize_vctk.py](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/use_mfa/local/reorganize_vctk.py)): +You can download from here [vctk_alignment.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/VCTK-Corpus-0.92/vctk_alignment.tar.gz), or train your own MFA model reference to [use_mfa example](https://github.com/PaddlePaddle/DeepSpeech/tree/develop/examples/other/use_mfa) of our repo. +ps: we remove three speakers in VCTK-0.92 (see [reorganize_vctk.py](https://github.com/PaddlePaddle/DeepSpeech/blob/develop/examples/other/use_mfa/local/reorganize_vctk.py)): 1. `p315`, because no txt for it. 2. `p280` and `p362`, because no *_mic2.flac (which is better than *_mic1.flac) for them.