From 58f04f2b873831f8b40ff3d181fc5ec2a720e327 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eren=20G=C3=B6lge?= Date: Mon, 11 Jan 2021 01:52:35 +0100 Subject: [PATCH 1/2] logo update --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 9733c966..2d394b17 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,5 @@ - + # TTS: Text-to-Speech for all. From 313e017fdea027f781a71c30c7b3448cbf452a06 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Eren=20G=C3=B6lge?= Date: Mon, 11 Jan 2021 02:12:08 +0100 Subject: [PATCH 2/2] Update README.md --- README.md | 25 ++++++++++++------------- 1 file changed, 12 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index 2d394b17..ee7e5714 100644 --- a/README.md +++ b/README.md @@ -21,15 +21,24 @@ Please use our dedicated channels for questions and discussion. Help is much mor | Type | Platforms | | ------------------------------- | --------------------------------------- | | 🚨 **Bug Reports** | [GitHub Issue Tracker] | -| 🎁 **Feature Requests & Ideas** | [GitHub Issue Tracker] | +| ❔ **FAQ** | [TTS/Wiki](https://github.com/mozilla/TTS/wiki/FAQ) | +| 🎁 **Feature Requests & Ideas** | [GitHub Issue Tracker] | | 👩‍💻 **Usage Questions** | [Discourse Forum] | | 🗯 **General Discussion** | [Discourse Forum] and [Matrix Channel] | [github issue tracker]: https://github.com/mozilla/tts/issues [discourse forum]: https://discourse.mozilla.org/c/tts/ [matrix channel]: https://matrix.to/#/!KTePhNahjgiVumkqca:matrix.org?via=matrix.org +[Tutorials and Examples]: https://github.com/mozilla/TTS/wiki/TTS-Notebooks-and-Tutorials +## 🔗 Links and Resources +| Type | Links | +| ------------------------------- | --------------------------------------- | +| 👩🏾‍🏫 **Tutorials and Examples** | [TTS/Wiki](https://github.com/mozilla/TTS/wiki/TTS-Notebooks-and-Tutorials) | +| 🤖 **Released Models** | [TTS/Wiki](https://github.com/mozilla/TTS/wiki/Released-Models)| +| 💻 **Docker Image** | [Repository by @synesthesiam](https://github.com/synesthesiam/docker-mozillatts)| + ## 🥇 TTS Performance

@@ -82,7 +91,7 @@ TTS supports **python >= 3.6**. ```python setup.py install``` or ```python setup.py develop``` to keep your installation in your working directory. -### Directory Structure +## Directory Structure ``` |- notebooks/ (Jupyter Notebooks for model evaluation, parameter selection and data analysis.) |- utils/ (common utilities.) @@ -103,12 +112,6 @@ TTS supports **python >= 3.6**. |- (same) ``` -### Docker -A docker image is created by [@synesthesiam](https://github.com/synesthesiam) and shared in a separate [repository](https://github.com/synesthesiam/docker-mozillatts) with the latest LJSpeech models. - -## Released Models -Please visit [our wiki.](https://github.com/mozilla/TTS/wiki/Released-Models) - ## Sample Model Output Below you see Tacotron model state after 16K iterations with batch-size 32 with LJSpeech dataset. @@ -118,8 +121,6 @@ Audio examples: [soundcloud](https://soundcloud.com/user-565970875/pocket-articl example_output -## [TTS Tutorials and Notebooks](https://github.com/mozilla/TTS/wiki/TTS-Notebooks-and-Tutorials) - ## Datasets and Data-Loading TTS provides a generic dataloader easy to use for your custom dataset. You just need to write a simple function to format the dataset. Check ```datasets/preprocess.py``` to see some examples. @@ -134,7 +135,7 @@ Some of the public datasets that we successfully applied TTS: - [LibriTTS](https://openslr.org/60/) - [Spanish](https://drive.google.com/file/d/1Sm_zyBo67XHkiFhcRSQ4YaHPYM0slO_e/view?usp=sharing) - thx! @carlfm01 -## Training and Fine-tuning LJ-Speech +## Example: Training and Fine-tuning LJ-Speech Dataset Here you can find a [CoLab](https://gist.github.com/erogol/97516ad65b44dbddb8cd694953187c5b) notebook for a hands-on example, training LJSpeech. Or you can manually follow the guideline below. To start with, split ```metadata.csv``` into train and validation subsets respectively ```metadata_train.csv``` and ```metadata_val.csv```. Note that for text-to-speech, validation performance might be misleading since the loss value does not directly measure the voice quality to the human ear and it also does not measure the attention module performance. Therefore, running the model with new sentences and listening to the results is the best way to go. @@ -187,8 +188,6 @@ If you like to use TTS to try a new idea and like to share your experiments with - Explain your idea and experiment. - Share your results regularly. (Tensorboard log files, audio results, visuals etc.) -## [Contact/Getting Help](https://github.com/mozilla/TTS/wiki/Contact-and-Getting-Help) - ## Major TODOs - [x] Implement the model. - [x] Generate human-like speech on LJSpeech dataset.