diff --git a/docs/source/released_model.md b/docs/source/released_model.md index ffe721b8f28e25ff186396c02f578660b532165c..52b386daf3e43698b7fa74080425f28770489353 100644 --- a/docs/source/released_model.md +++ b/docs/source/released_model.md @@ -49,11 +49,12 @@ Model Type | Dataset| Example Link | Pretrained Models| Static Models|Size (stat WaveFlow| LJSpeech |[waveflow-ljspeech](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/ljspeech/voc0)|[waveflow_ljspeech_ckpt_0.3.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/waveflow/waveflow_ljspeech_ckpt_0.3.zip)||| Parallel WaveGAN| CSMSC |[PWGAN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc1)|[pwg_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_baker_ckpt_0.4.zip)|[pwg_baker_static_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_baker_static_0.4.zip)|5.1MB| Parallel WaveGAN| LJSpeech |[PWGAN-ljspeech](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/ljspeech/voc1)|[pwg_ljspeech_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/pwgan/pwg_ljspeech_ckpt_0.5.zip)||| -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| 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_csmsc_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/mb_melgan/mb_melgan_csmsc_ckpt_0.1.1.zip)
[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_csmsc_static_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/mb_melgan/mb_melgan_csmsc_static_0.1.1.zip) |8.2MB| Style MelGAN | CSMSC |[Style MelGAN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc4)|[style_melgan_csmsc_ckpt_0.1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/style_melgan/style_melgan_csmsc_ckpt_0.1.1.zip)| | | 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| +HiFiGAN | AISHELL-3 |[HiFiGAN-aishell3](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/voc5)|[hifigan_aishell3_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip)||| WaveRNN | CSMSC |[WaveRNN-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/voc6)|[wavernn_csmsc_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/wavernn/wavernn_csmsc_ckpt_0.2.0.zip)|[wavernn_csmsc_static_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/wavernn/wavernn_csmsc_static_0.2.0.zip)|18MB| diff --git a/examples/aishell3/voc5/README.md b/examples/aishell3/voc5/README.md index 7cd0b39639f4b6d5867a62b36ef83be1192fb693..ebe2530beec58e87fa55f8ce6a203260858a21f8 100644 --- a/examples/aishell3/voc5/README.md +++ b/examples/aishell3/voc5/README.md @@ -135,8 +135,22 @@ optional arguments: 3. `--test-metadata` is the metadata of the test dataset. Use the `metadata.jsonl` in the `dev/norm` subfolder from the processed directory. 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. - ## Pretrained Models +The pretrained model can be downloaded here [hifigan_aishell3_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/hifigan/hifigan_aishell3_ckpt_0.2.0.zip). + + +Model | Step | eval/generator_loss | eval/mel_loss| eval/feature_matching_loss +:-------------:| :------------:| :-----: | :-----: | :--------: +default| 1(gpu) x 2500000|24.060|0.1068|7.499 + +HiFiGAN checkpoint contains files listed below. + +```text +hifigan_aishell3_ckpt_0.2.0 +├── default.yaml # default config used to train hifigan +├── feats_stats.npy # statistics used to normalize spectrogram when training hifigan +└── snapshot_iter_2500000.pdz # generator parameters of hifigan +``` ## Acknowledgement We adapted some code from https://github.com/kan-bayashi/ParallelWaveGAN. diff --git a/paddlespeech/t2s/exps/synthesize.py b/paddlespeech/t2s/exps/synthesize.py index 426b7617fb62ef9759d0d9fb63f72b396f92eb79..abb1eb4eb6e395b835c56d64faa226d51e8049ea 100644 --- a/paddlespeech/t2s/exps/synthesize.py +++ b/paddlespeech/t2s/exps/synthesize.py @@ -156,6 +156,7 @@ def parse_args(): choices=[ 'pwgan_csmsc', 'pwgan_ljspeech', 'pwgan_aishell3', 'pwgan_vctk', 'mb_melgan_csmsc', 'wavernn_csmsc', 'hifigan_csmsc', + 'hifigan_ljspeech', 'hifigan_aishell3', 'hifigan_vctk', 'style_melgan_csmsc' ], help='Choose vocoder type of tts task.') diff --git a/paddlespeech/t2s/exps/synthesize_e2e.py b/paddlespeech/t2s/exps/synthesize_e2e.py index 3d01bdb011bab9c86980cace41dfa0b31a6d797d..f5214d4a48b1bc395cccc627208f672d1f8df0ca 100644 --- a/paddlespeech/t2s/exps/synthesize_e2e.py +++ b/paddlespeech/t2s/exps/synthesize_e2e.py @@ -180,9 +180,17 @@ def parse_args(): type=str, default='pwgan_csmsc', choices=[ - 'pwgan_csmsc', 'pwgan_ljspeech', 'pwgan_aishell3', 'pwgan_vctk', - 'mb_melgan_csmsc', 'style_melgan_csmsc', 'hifigan_csmsc', - 'wavernn_csmsc' + 'pwgan_csmsc', + 'pwgan_ljspeech', + 'pwgan_aishell3', + 'pwgan_vctk', + 'mb_melgan_csmsc', + 'style_melgan_csmsc', + 'hifigan_csmsc', + 'hifigan_ljspeech', + 'hifigan_aishell3', + 'hifigan_vctk', + 'wavernn_csmsc', ], help='Choose vocoder type of tts task.') parser.add_argument(