diff --git a/README.md b/README.md index eccf70373d83945220ddba846994a4537b4aa3bf..5093dbd678a895026a5021c655f944adc202054f 100644 --- a/README.md +++ b/README.md @@ -463,10 +463,10 @@ PaddleSpeech supports a series of most popular models. They are summarized in [r - GE2E + Tactron2 + GE2E + Tacotron2 AISHELL-3 - ge2e-tactron2-aishell3 + ge2e-tacotron2-aishell3 diff --git a/README_cn.md b/README_cn.md index f8f84ca870ad772fdd211e41d91b1ba9c6d2d5a6..5dab7fa0c034fe778c7f7c10e65a78fb6c3e52b5 100644 --- a/README_cn.md +++ b/README_cn.md @@ -450,10 +450,10 @@ PaddleSpeech 的 **语音合成** 主要包含三个模块：文本前端、声 - GE2E + Tactron2 + GE2E + Tacotron2 AISHELL-3 - ge2e-tactron2-aishell3 + ge2e-tacotron2-aishell3 diff --git a/docs/source/released_model.md b/docs/source/released_model.md index 2b2aedb71e568cfb4dca86d3c2ee9f13f8fe47bd..4b7f67373a886f19e07e1ca45fbe772a087dd235 100644 --- a/docs/source/released_model.md +++ b/docs/source/released_model.md @@ -37,8 +37,8 @@ Model Type | Dataset| Example Link | Pretrained Models|Static Models|Size (stati Tacotron2|LJSpeech|[tacotron2-ljspeech](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/ljspeech/tts0)|[tacotron2_ljspeech_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/tacotron2/tacotron2_ljspeech_ckpt_0.2.0.zip)||| Tacotron2|CSMSC|[tacotron2-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/tts0)|[tacotron2_csmsc_ckpt_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/tacotron2/tacotron2_csmsc_ckpt_0.2.0.zip)|[tacotron2_csmsc_static_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/tacotron2/tacotron2_csmsc_static_0.2.0.zip)|103MB| TransformerTTS| LJSpeech| [transformer-ljspeech](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/ljspeech/tts1)|[transformer_tts_ljspeech_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/transformer_tts/transformer_tts_ljspeech_ckpt_0.4.zip)||| -SpeedySpeech| CSMSC | [speedyspeech-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/tts2) |[speedyspeech_nosil_baker_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/speedyspeech/speedyspeech_nosil_baker_ckpt_0.5.zip)|[speedyspeech_nosil_baker_static_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/speedyspeech/speedyspeech_nosil_baker_static_0.5.zip)|12MB| -FastSpeech2| CSMSC |[fastspeech2-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/tts3)|[fastspeech2_nosil_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_nosil_baker_ckpt_0.4.zip)|[fastspeech2_nosil_baker_static_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_nosil_baker_static_0.4.zip)|157MB| +SpeedySpeech| CSMSC | [speedyspeech-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/tts2) |[speedyspeech_nosil_baker_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/speedyspeech/speedyspeech_nosil_baker_ckpt_0.5.zip)|[speedyspeech_csmsc_static_2.0.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/speedyspeech/speedyspeech_csmsc_static_2.0.0.zip)|12MB| +FastSpeech2| CSMSC |[fastspeech2-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/tts3)|[fastspeech2_nosil_baker_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_nosil_baker_ckpt_0.4.zip)|fastspeech2_csmsc_static_0.2.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_csmsc_static_0.2.0.zip)|157MB| FastSpeech2-Conformer| CSMSC |[fastspeech2-csmsc](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/csmsc/tts3)|[fastspeech2_conformer_baker_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_conformer_baker_ckpt_0.5.zip)||| FastSpeech2| AISHELL-3 |[fastspeech2-aishell3](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/aishell3/tts3)|[fastspeech2_nosil_aishell3_ckpt_0.4.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_nosil_aishell3_ckpt_0.4.zip)||| FastSpeech2| LJSpeech |[fastspeech2-ljspeech](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/ljspeech/tts3)|[fastspeech2_nosil_ljspeech_ckpt_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/fastspeech2/fastspeech2_nosil_ljspeech_ckpt_0.5.zip)||| diff --git a/examples/csmsc/tts2/README.md b/examples/csmsc/tts2/README.md index bb27fb0ce36848c3b3b05e02b0939e1280900f25..e26d9c3226e2768eed5c2ee3737bc793f4405c34 100644 --- a/examples/csmsc/tts2/README.md +++ b/examples/csmsc/tts2/README.md @@ -226,6 +226,7 @@ Pretrained SpeedySpeech model with no silence in the edge of audios: The static model can be downloaded here: - [speedyspeech_nosil_baker_static_0.5.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/speedyspeech/speedyspeech_nosil_baker_static_0.5.zip) +- [speedyspeech_csmsc_static_2.0.0.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/speedyspeech/speedyspeech_csmsc_static_2.0.0.zip) Model | Step | eval/loss | eval/l1_loss | eval/duration_loss | eval/ssim_loss :-------------:| :------------:| :-----: | :-----: | :--------:|:--------: diff --git a/examples/csmsc/tts3/run.sh b/examples/csmsc/tts3/run.sh index 325b2707ac9a2f0246d427c040df091178534932..94f532532e1934dd92ef4ca17e9b8ec6adaa8c1b 100755 --- a/examples/csmsc/tts3/run.sh +++ b/examples/csmsc/tts3/run.sh @@ -52,6 +52,6 @@ fi # inference with onnxruntime, use fastspeech2 + hifigan by default if [ ${stage} -le 6 ] && [ ${stop_stage} -ge 6 ]; then - # pip install onnxruntime + pip install onnxruntime ./local/ort_predict.sh ${train_output_path} fi