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

update hifigan readme, test=doc_fix

Browse Source
pull/1181/head
TianYuan 3 years ago
parent d561742f27
commit d607629e1a
6 changed files with 32 additions and 12 deletions
Show Stats Download Patch File Download Diff File

13
docs/source/released_model.md
Unescape View File

@ -1,3 +1,4 @@
# Released Models
## Speech-to-Text Models
@ -51,6 +52,7 @@ Parallel WaveGAN| LJSpeech |[PWGAN-ljspeech](https://github.com/PaddlePaddle/Pad
Parallel WaveGAN|AISHELL-3 |[PWGAN-aishell3](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc1)|[pwg_aishell3_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_aishell3_ckpt_0.5.zip)|||
Parallel WaveGAN| VCTK |[PWGAN-vctk](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/vctk/voc1)|[pwg_vctk_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_vctk_ckpt_0.5.zip)|||
|Multi Band MelGAN |CSMSC|[MB MelGAN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc3) | [mb_melgan_baker_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/mb_melgan/mb_melgan_baker_ckpt_0.5.zip) <br>[mb_melgan_baker_finetune_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/mb_melgan/mb_melgan_baker_finetune_ckpt_0.5.zip)|[mb_melgan_baker_static_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/mb_melgan/mb_melgan_baker_static_0.5.zip) |8.2MB|
HiFiGAN | CSMSC |[HiFiGAN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc5)|[hifigan_csmsc_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_csmsc_ckpt_0.1.1.zip)|[hifigan_csmsc_static_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_csmsc_static_0.1.1.zip)|50MB|
### Voice Cloning
Model Type | Dataset| Example Link | Pretrained Models
@ -67,11 +69,10 @@ Model Type | Dataset| Example Link | Pretrained Models
PANN | Audioset| [audioset_tagging_cnn](https://github.com/qiuqiangkong/audioset_tagging_cnn) | [panns_cnn6.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn6.pdparams),[panns_cnn10.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn10.pdparams),[panns_cnn14.pdparams](https://bj.bcebos.com/paddleaudio/models/panns_cnn14.pdparams)
PANN | ESC-50 |[pann-esc50]("./examples/esc50/cls0")|[panns_cnn6.tar.gz](https://paddlespeech.bj.bcebos.com/cls/panns_cnn6.tar.gz), [panns_cnn10](https://paddlespeech.bj.bcebos.com/cls/panns_cnn10.tar.gz), [panns_cnn14.tar.gz](https://paddlespeech.bj.bcebos.com/cls/panns_cnn14.tar.gz)
## Speech Recognition Model from paddle 1.8
| Acoustic Model | Training Data | Token-based | Size | Descriptions | CER | WER | Hours of speech |
| :----------------------------------------------------------: | :----------------------------: | :---------: | -----: | :------------------------------------------------- | :----- | :----- | :-------------- |
| [Ds2 Offline Aishell model](https://deepspeech.bj.bcebos.com/mandarin_models/aishell_model_v1.8_to_v2.x.tar.gz) | Aishell Dataset | Char-based | 234 MB | 2 Conv + 3 bidirectional GRU layers | 0.0804 | - | 151 h |
| [Ds2 Offline Librispeech model](https://deepspeech.bj.bcebos.com/eng_models/librispeech_v1.8_to_v2.x.tar.gz) | Librispeech Dataset | Word-based | 307 MB | 2 Conv + 3 bidirectional sharing weight RNN layers | - | 0.0685 | 960 h |
| [Ds2 Offline Baidu en8k model](https://deepspeech.bj.bcebos.com/eng_models/baidu_en8k_v1.8_to_v2.x.tar.gz) | Baidu Internal English Dataset | Word-based | 273 MB | 2 Conv + 3 bidirectional GRU layers | - | 0.0541 | 8628 h |
| Acoustic Model |Training Data| Token-based | Size | Descriptions | CER | WER | Hours of speech |
| :--------------: | :--------------: | :--------------: | :--------------: | :--------------: | :--------------: | :--------------: | :--------------: |
| [Ds2 Offline Aishell model](https://deepspeech.bj.bcebos.com/mandarin_models/aishell_model_v1.8_to_v2.x.tar.gz) | Aishell Dataset | Char-based | 234 MB | 2 Conv + 3 bidirectional GRU layers | 0.0804 | — | 151 h |
| [Ds2 Offline Librispeech model](https://deepspeech.bj.bcebos.com/eng_models/librispeech_v1.8_to_v2.x.tar.gz) | Librispeech Dataset | Word-based | 307 MB | 2 Conv + 3 bidirectional sharing weight RNN layers | — | 0.0685 | 960 h |
| [Ds2 Offline Baidu en8k model](https://deepspeech.bj.bcebos.com/eng_models/baidu_en8k_v1.8_to_v2.x.tar.gz) | Baidu Internal English Dataset | Word-based | 273 MB | 2 Conv + 3 bidirectional GRU layers |— | 0.0541 | 8628 h |

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

@ -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 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.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.
## Get Started
Assume the path to the dataset is `~/datasets/BZNSYP`.

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

@ -134,7 +134,7 @@ The pretrained model can be downloaded here [pwg_baker_ckpt_0.4.zip](https://pad
The static model can be downloaded here [pwg_baker_static_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_baker_static_0.4.zip).
Model | Step | eval/generator_loss | eval/log_stft_magnitude_loss:| eval/spectral_convergence_loss
Model | Step | eval/generator_loss | eval/log_stft_magnitude_loss| eval/spectral_convergence_loss
:-------------:| :------------:| :-----: | :-----: | :--------:
default| 1(gpu) x 400000|1.948763|0.670098|0.248882

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

@ -6,7 +6,7 @@ Download CSMSC from the [official website](https://www.data-baker.com/data/index
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut the silence in the edge of audio.
You can download from here [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/Parakeet/tree/develop/examples/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 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`.

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

@ -6,7 +6,7 @@ Download CSMSC from the [official website](https://www.data-baker.com/data/index
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut the silence in the edge of audio.
You can download from here [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/Parakeet/tree/develop/examples/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 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`.

23
examples/csmsc/voc5/README.md
Unescape View File

@ -6,7 +6,7 @@ Download CSMSC from the [official website](https://www.data-baker.com/data/index
### Get MFA Result and Extract
We use [MFA](https://github.com/MontrealCorpusTools/Montreal-Forced-Aligner) results to cut silence at 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 MFA model reference to [mfa example](https://github.com/PaddlePaddle/Parakeet/tree/develop/examples/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 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`.
@ -114,4 +114,23 @@ optional arguments:
4. `--output-dir` is the directory to save the synthesized audio files.
5. `--ngpu` is the number of gpus to use, if ngpu == 0, use cpu.
## Fine-tuning
## Pretrained Models
The pretrained model can be downloaded here [hifigan_csmsc_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_csmsc_ckpt_0.1.1.zip).
The static model can be downloaded here [hifigan_csmsc_static_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_csmsc_static_0.1.1.zip)
Model | Step | eval/generator_loss | eval/mel_loss| eval/feature_matching_loss
:-------------:| :------------:| :-----: | :-----: | :--------:
default| 1(gpu) x 2500000|24.927|0.1262|7.554
HiFiGAN checkpoint contains files listed below.
```text
hifigan_csmsc_ckpt_0.1.1
├── default.yaml # default config used to train hifigan
├── feats_stats.npy # generator parameters of hifigan
└── snapshot_iter_2500000.pdz # statistics used to normalize spectrogram when training hifigan
```
## Acknowledgement
We adapted some code from https://github.com/kan-bayashi/ParallelWaveGAN.
Write Preview
Loading…
Cancel
Save