> If you encounter problem with downloading **nltk_data** while using paddlespeech, it maybe due to your poor network, we suggest you download the [nltk_data](https://paddlespeech.bj.bcebos.com/Parakeet/tools/nltk_data.tar.gz) provided by us, and extract it to your `${HOME}`.
> If you encounter problem with downloading **nltk_data** while using paddlespeech, it maybe due to your poor network, we suggest you download the [nltk_data](https://paddlespeech.cdn.bcebos.com/Parakeet/tools/nltk_data.tar.gz) provided by us, and extract it to your `${HOME}`.
> If you fail to install paddlespeech-ctcdecoders, you only can not use deepspeech2 model inference. For other models, it doesn't matter.
Parallel WaveGAN| Male ||[pwg_male_ckpt_1.4.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_male_ckpt_1.4.0.zip)|[pwgan_male_static_1.4.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwgan_male_static_1.4.0.zip) </br> [pwgan_male_onnx_1.4.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwgan_male_onnx_1.4.0.zip)|4.8M|
HiFiGAN| Male ||[hifigan_male_ckpt_1.4.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_male_ckpt_1.4.0.zip)|[hifigan_male_static_1.4.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_male_static_1.4.0.zip) </br> [hifigan_male_onnx_1.4.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_male_onnx_1.4.0.zip)|46M|
Parallel WaveGAN| Male ||[pwg_male_ckpt_1.4.0.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwg_male_ckpt_1.4.0.zip)|[pwgan_male_static_1.4.0.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwgan_male_static_1.4.0.zip) </br> [pwgan_male_onnx_1.4.0.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwgan_male_onnx_1.4.0.zip)|4.8M|
HiFiGAN| Male ||[hifigan_male_ckpt_1.4.0.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/hifigan/hifigan_male_ckpt_1.4.0.zip)|[hifigan_male_static_1.4.0.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/hifigan/hifigan_male_static_1.4.0.zip) </br> [hifigan_male_onnx_1.4.0.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/hifigan/hifigan_male_onnx_1.4.0.zip)|46M|
### Voice Cloning
Model Type | Dataset| Example Link | Pretrained Models
GE2E| AISHELL-3, etc. |[ge2e](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/ge2e)|[ge2e_ckpt_0.3.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/ge2e/ge2e_ckpt_0.3.zip)
GE2E| AISHELL-3, etc. |[ge2e](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/ge2e)|[ge2e_ckpt_0.3.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/ge2e/ge2e_ckpt_0.3.zip)
Ernie Linear | IWLST2012_zh |[iwslt2012_punc0](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/iwslt2012/punc0)|[ernie_linear_p3_iwslt2012_zh_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/text/ernie_linear_p3_iwslt2012_zh_ckpt_0.1.1.zip)
Ernie Linear | IWLST2012_zh |[iwslt2012_punc0](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/iwslt2012/punc0)|[ernie_linear_p3_iwslt2012_zh_ckpt_0.1.1.zip](https://paddlespeech.cdn.bcebos.com/text/ernie_linear_p3_iwslt2012_zh_ckpt_0.1.1.zip)
You need to prepare an audio file or use the audio demo above, please confirm the sample rate of the audio is 16K. You can get the result of the audio demo by running the script below.
tar xzvf asr1_transformer_aishell_ckpt_0.1.1.model.tar.gz
source path.sh
# If you have process the data and get the manifest file， you can skip the following 2 steps
@ -195,12 +195,12 @@ In some situations, you want to use the trained model to do the inference for th
```
you can train the model by yourself using ```bash run.sh --stage 0 --stop_stage 3```, or you can download the pretrained model through the script below:
You need to prepare an audio file or use the audio demo above, please confirm the sample rate of the audio is 16K. You can get the result by running the script below.
tar xzvf wav2vec2ASR-large-aishell1_ckpt_1.4.0.model.tar.gz
source path.sh
# If you have process the data and get the manifest file， you can skip the following 2 steps
@ -185,12 +185,12 @@ In some situations, you want to use the trained model to do the inference for th
```
you can train the model by yourself using ```bash run.sh --stage 0 --stop_stage 3```, or you can download the pretrained model through the script below:
You need to prepare an audio file or use the audio demo above, please confirm the sample rate of the audio is 16K. You can get the result of the audio demo by running the script below.
@ -16,7 +16,7 @@ Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishe
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for aishell3_fastspeech2.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
## Get Started
Assume the path to the dataset is `~/datasets/data_aishell3`.
We use [HiFiGAN](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc5) as the neural vocoder.
Download pretrained HiFiGAN model from [hifigan_aishell3_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip) and unzip it.
Download pretrained HiFiGAN model from [hifigan_aishell3_ckpt_0.2.0.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip) and unzip it.
@ -143,7 +143,7 @@ You can check the text of downloaded wavs in `source/README.md`.
You can modify `--wav_path`、`--old_str` and `--new_str` yourself, `--old_str` should be the text corresponding to the audio of `--wav_path`, `--new_str` should be designed according to `--task_name`, both `--source_lang` and `--target_lang` should be `zh` for model trained with AISHELL3 dataset.
@ -10,7 +10,7 @@ Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishe
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for aishell3_fastspeech2.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
## Get Started
Assume the path to the dataset is `~/datasets/data_aishell3`.
@ -96,7 +96,7 @@ optional arguments:
### Synthesizing
We use [parallel wavegan](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc1) as the neural vocoder.
Download the pretrained parallel wavegan model from [pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip) and unzip it.
Download the pretrained parallel wavegan model from [pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip) and unzip it.
```bash
unzip pwg_aishell3_ckpt_0.5.zip
```
@ -219,20 +219,20 @@ optional arguments:
## Pretrained Model
Pretrained FastSpeech2 model with no silence in the edge of audios:
- [fastspeech2_aishell3_static_pir_1.1.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_aishell3_static_pir_1.1.0.zip) (Run PIR model need to set FLAGS_enable_pir_api=1, and PIR model only worked with paddlepaddle>=3.0.0b2)
- [fastspeech2_aishell3_static_pir_1.1.0.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_aishell3_static_pir_1.1.0.zip) (Run PIR model need to set FLAGS_enable_pir_api=1, and PIR model only worked with paddlepaddle>=3.0.0b2)
@ -10,7 +10,7 @@ Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishe
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get phonemes for Tacotron2, the durations of MFA are not needed here.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
## Pretrained GE2E Model
We use pretrained GE2E model to generate speaker embedding for each sentence.
@ -79,7 +79,7 @@ The training step is very similar to that one of [tts0](https://github.com/Paddl
### Synthesizing
We use [parallel wavegan](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc1) as the neural vocoder.
Download pretrained parallel wavegan model from [pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip) and unzip it.
Download pretrained parallel wavegan model from [pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip) and unzip it.
@ -10,7 +10,7 @@ Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishe
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for aishell3_fastspeech2.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
## Pretrained GE2E Model
We use pretrained GE2E model to generate speaker embedding for each sentence.
@ -81,7 +81,7 @@ The training step is very similar to that one of [tts3](https://github.com/Paddl
### Synthesizing
We use [parallel wavegan](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc1) as the neural vocoder.
Download pretrained parallel wavegan model from [pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip) and unzip it.
Download pretrained parallel wavegan model from [pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip) and unzip it.
@ -10,7 +10,7 @@ Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishe
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for aishell3_fastspeech2.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
## Get Started
Assume the path to the dataset is `~/datasets/data_aishell3`.
@ -75,7 +75,7 @@ The training step is very similar to that one of [tts3](https://github.com/Paddl
### Synthesizing
We use [parallel wavegan](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc1) as the neural vocoder.
Download pretrained parallel wavegan model from [pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip) and unzip it.
Download pretrained parallel wavegan model from [pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip) and unzip it.
@ -9,7 +9,7 @@ Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishe
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get phonemes for VITS, the durations of MFA are not needed here.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
## Pretrained GE2E Model
We use pretrained GE2E model to generate speaker embedding for each sentence.
@ -10,7 +10,7 @@ Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishe
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get phonemes for VITS, the durations of MFA are not needed here.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
## Get Started
Assume the path to the dataset is `~/datasets/data_aishell3`.
@ -8,7 +8,7 @@ Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishe
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for aishell3_fastspeech2.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
## Get Started
Assume the path to the dataset is `~/datasets/data_aishell3`.
- [pwgan_aishell3_static_pir_1.1.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwgan_aishell3_static_pir_1.1.0.zip) (Run PIR model need to set FLAGS_enable_pir_api=1, and PIR model only worked with paddlepaddle>=3.0.0b2)
- [pwgan_aishell3_static_pir_1.1.0.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwgan_aishell3_static_pir_1.1.0.zip) (Run PIR model need to set FLAGS_enable_pir_api=1, and PIR model only worked with paddlepaddle>=3.0.0b2)
@ -7,7 +7,7 @@ AISHELL-3 is a large-scale and high-fidelity multi-speaker Mandarin speech corpu
Download AISHELL-3 from it's [Official Website](http://www.aishelltech.com/aishell_3) and extract it to `~/datasets`. Then the dataset is in the directory `~/datasets/data_aishell3`.
### Get MFA Result and Extract
We use [MFA2.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for aishell3_fastspeech2.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.bj.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
You can download from here [aishell3_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/AISHELL-3/with_tone/aishell3_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
## Get Started
Assume the path to the dataset is `~/datasets/data_aishell3`.
@ -114,19 +114,19 @@ optional arguments:
5. `--ngpu` is the number of gpus to use, if ngpu == 0, use cpu.
- [hifigan_aishell3_static_pir_1.1.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_static_pir_1.1.0.zip) (Run PIR model need to set FLAGS_enable_pir_api=1, and PIR model only worked with paddlepaddle>=3.0.0b2)
- [hifigan_aishell3_static_pir_1.1.0.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_static_pir_1.1.0.zip) (Run PIR model need to set FLAGS_enable_pir_api=1, and PIR model only worked with paddlepaddle>=3.0.0b2)
Or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
We use [HiFiGAN](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc5) as the neural vocoder.
Download pretrained HiFiGAN model from [hifigan_aishell3_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip) and unzip it.
Download pretrained HiFiGAN model from [hifigan_aishell3_ckpt_0.2.0.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip) and unzip it.
You can check the text of downloaded wavs in `source/README.md`.
@ -155,7 +155,7 @@ You can check the text of downloaded wavs in `source/README.md`.
You can modify `--wav_path`、`--old_str` and `--new_str` yourself, `--old_str` should be the text corresponding to the audio of `--wav_path`, `--new_str` should be designed according to `--task_name`, `--source_lang` and `--target_lang` should be different in this example.
@ -27,7 +27,7 @@ After that, it should be look like:
### Get MFA Result and Extract
We use [MFA1.x](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get durations for canton_fastspeech2.
You can train your MFA model reference to [canton_mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) (use MFA1.x now) of our repo.
We here provide the MFA results of these two datasets. [canton_alignment.zip](https://paddlespeech.bj.bcebos.com/MFA/Canton/canton_alignment.zip)
We here provide the MFA results of these two datasets. [canton_alignment.zip](https://paddlespeech.cdn.bcebos.com/MFA/Canton/canton_alignment.zip)
## Get Started
Assume the path to the Cantonese MFA result of the two datsets mentioned above is `./canton_alignment`.
@ -77,13 +77,13 @@ Also, there is a `metadata.jsonl` in each subfolder. It is a table-like file tha
## Pretrained Model
Pretrained FastSpeech2 model with no silence in the edge of audios:
└── speech_stats.npy # statistics used to normalize spectrogram when training fastspeech2
```
We use [parallel wavegan](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc1) as the neural vocoder.
Download the pretrained parallel wavegan model from [pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip) and unzip it.
Download the pretrained parallel wavegan model from [pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip) and unzip it.
@ -18,7 +18,7 @@ The structure of the folder is listed below.
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get phonemes and durations for JETS.
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 MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
## Get Started
Assume the path to the dataset is `~/datasets/BZNSYP`.
@ -7,7 +7,7 @@ Download CSMSC from it's [Official Website](https://test.data-baker.com/data/ind
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) to get phonemes for Tacotron2, the durations of MFA are not needed here.
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 MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
## Get Started
Assume the path to the dataset is `~/datasets/BZNSYP`.
@ -86,7 +86,7 @@ optional arguments:
### Synthesizing
We use [parallel wavegan](https://github.com/PaddlePaddle/PaddleSpeech/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/released_models/pwgan/pwg_baker_ckpt_0.4.zip) and unzip it.
Download pretrained parallel wavegan model from [pwg_baker_ckpt_0.4.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwg_baker_ckpt_0.4.zip) and unzip it.
```bash
unzip pwg_baker_ckpt_0.4.zip
```
@ -208,10 +208,10 @@ optional arguments:
## Pretrained Model
Pretrained Tacotron2 model with no silence in the edge of audios:
@ -18,7 +18,7 @@ The structure of the folder is listed below.
### Get MFA Result and Extract
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 MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
## Get Started
Assume the path to the dataset is `~/datasets/BZNSYP`.
@ -103,7 +103,7 @@ optional arguments:
### Synthesizing
We use [parallel wavegan](https://github.com/PaddlePaddle/PaddleSpeech/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/released_models/pwgan/pwg_baker_ckpt_0.4.zip) and unzip it.
Download pretrained parallel wavegan model from [pwg_baker_ckpt_0.4.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwg_baker_ckpt_0.4.zip) and unzip it.
@ -8,7 +8,7 @@ Download CSMSC from it's [Official Website](https://test.data-baker.com/data/ind
### Get MFA Result and Extract
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 MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
You can download from here [baker_alignment_tone.tar.gz](https://paddlespeech.cdn.bcebos.com/MFA/BZNSYP/with_tone/baker_alignment_tone.tar.gz), or train your MFA model reference to [mfa example](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/other/mfa) of our repo.
## Get Started
Assume the path to the dataset is `~/datasets/BZNSYP`.
@ -94,7 +94,7 @@ optional arguments:
### Synthesizing
We use [parallel wavegan](https://github.com/PaddlePaddle/PaddleSpeech/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/released_models/pwgan/pwg_baker_ckpt_0.4.zip) and unzip it.
Download pretrained parallel wavegan model from [pwg_baker_ckpt_0.4.zip](https://paddlespeech.cdn.bcebos.com/Parakeet/released_models/pwgan/pwg_baker_ckpt_0.4.zip) and unzip it.
> please compile develop version of Paddle-Lite to export and run TTS models, cause TTS models are supported by https://github.com/PaddlePaddle/Paddle-Lite/pull/9587 and https://github.com/PaddlePaddle/Paddle-Lite/pull/9706
zxcd
6 months ago
committed by
GitHub