From c10f9a3699182a91d4c01afd65143ea39de44382 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Eren=20G=C3=B6lge?= <erogol@hotmail.com>
Date: Mon, 13 Mar 2023 12:42:20 +0100
Subject: [PATCH] Update docs (#2389)

* Update docs index

* Add MarryTTS docs

* Update docs index

* Add Overflow docs
---
 docs/source/index.md           |  3 ++-
 docs/source/marytts.md         |  0
 docs/source/models/overflow.md | 36 ++++++++++++++++++++++++++++++++++
 3 files changed, 38 insertions(+), 1 deletion(-)
 create mode 100644 docs/source/marytts.md
 create mode 100644 docs/source/models/overflow.md

diff --git a/docs/source/index.md b/docs/source/index.md
index 3f27ffb8..51735928 100644
--- a/docs/source/index.md
+++ b/docs/source/index.md
@@ -28,6 +28,7 @@
     formatting_your_dataset
     what_makes_a_good_dataset
     tts_datasets
+    marytts
 
 .. toctree::
     :maxdepth: 2
@@ -48,10 +49,10 @@
     models/vits.md
     models/forward_tts.md
     models/tacotron1-2.md
+    models/overflow.md
 
 .. toctree::
     :maxdepth: 2
     :caption: `vocoder` Models
 
 ```
-
diff --git a/docs/source/marytts.md b/docs/source/marytts.md
new file mode 100644
index 00000000..e69de29b
diff --git a/docs/source/models/overflow.md b/docs/source/models/overflow.md
new file mode 100644
index 00000000..09e270ea
--- /dev/null
+++ b/docs/source/models/overflow.md
@@ -0,0 +1,36 @@
+# Overflow TTS
+
+Neural HMMs are a type of neural transducer recently proposed for
+sequence-to-sequence modelling in text-to-speech. They combine the best features
+of classic statistical speech synthesis and modern neural TTS, requiring less
+data and fewer training updates, and are less prone to gibberish output caused
+by neural attention failures. In this paper, we combine neural HMM TTS with
+normalising flows for describing the highly non-Gaussian distribution of speech
+acoustics. The result is a powerful, fully probabilistic model of durations and
+acoustics that can be trained using exact maximum likelihood. Compared to
+dominant flow-based acoustic models, our approach integrates autoregression for
+improved modelling of long-range dependences such as utterance-level prosody.
+Experiments show that a system based on our proposal gives more accurate
+pronunciations and better subjective speech quality than comparable methods,
+whilst retaining the original advantages of neural HMMs. Audio examples and code
+are available at https://shivammehta25.github.io/OverFlow/.
+
+
+## Important resources & papers
+- HMM: https://de.wikipedia.org/wiki/Hidden_Markov_Model
+- OverflowTTS paper: https://arxiv.org/abs/2211.06892
+- Neural HMM: https://arxiv.org/abs/2108.13320
+- Audio Samples: https://shivammehta25.github.io/OverFlow/
+
+
+## OverflowConfig
+```{eval-rst}
+.. autoclass:: TTS.tts.configs.overflow_config.OverflowConfig
+    :members:
+```
+
+## Overflow Model
+```{eval-rst}
+.. autoclass:: TTS.tts.models.overflow.Overflow
+    :members:
+```
\ No newline at end of file