Update README.md

README.md

@@ -7,14 +7,12 @@ tags:
 - acoustic modelling
 - speech
 - multispeaker
+- tts
 pipeline_tag: text-to-speech
 license: cc-by-nc-4.0
-datasets:
-- projecte-aina/festcat_trimmed_denoised
-- openslr
 ---
 
-# Matcha-TTS Catalan Multiaccent
+# Matxa-TTS (Matcha-TTS) Catalan Multiaccent
 
 ## Table of Contents
 <details>
@@ -32,23 +30,27 @@ datasets:
 
 ## Model Description
 
-**Matcha-TTS** is an encoder-decoder architecture designed for fast acoustic modelling in TTS. 
+**Matxa-TTS** is based on **Matcha-TTS** that is an encoder-decoder architecture designed for fast acoustic modelling in TTS. 
 The encoder part is based on a text encoder and a phoneme duration prediction that together predict averaged acoustic features.
 And the decoder has essentially a U-Net backbone inspired by [Grad-TTS](https://arxiv.org/pdf/2105.06337.pdf), which is based on the Transformer architecture. 
 In the latter, by replacing 2D CNNs by 1D CNNs, a large reduction in memory consumption and fast synthesis is achieved.
 
-**Matcha-TTS** is a non-autorregressive model trained with optimal-transport conditional flow matching (OT-CFM). 
+**Matxa-TTS** is a non-autorregressive model trained with optimal-transport conditional flow matching (OT-CFM). 
 This yields an ODE-based decoder capable of generating high output quality in fewer synthesis steps than models trained using score matching.
 
 ## Intended Uses and Limitations
 
 This model is intended to serve as an acoustic feature generator for multispeaker text-to-speech systems for the Catalan language. 
-It has been finetuned using a Catalan phonemizer, therefore if the model is used for other languages it may will not produce intelligible samples after mapping 
+It has been finetuned using a Catalan phonemizer, therefore if the model is used for other languages it will not produce intelligible samples after mapping 
 its output into a speech waveform. 
 
 The quality of the samples can vary depending on the speaker. 
 This may be due to the sensitivity of the model in learning specific frequencies and also due to the quality of samples for each speaker.
 
+As explained in the licenses section, the models can be used only for non-commercial purposes. Any parties interested in using them
+commercially need to contact the rights holders, the voice artists for licensing their voices. For more information see the licenses section
+under [Additional information](#additional-information).
+
 ## How to Get Started with the Model
 
 ### Installation
@@ -64,7 +66,7 @@ python -m venv /path/to/venv
 source /path/to/venv/bin/activate
 ```
 
-For training and inferencing with Catalan Matcha-TTS you need to compile the provided espeak-ng with the Catalan phonemizer:
+For training and synthesizing with Catalan Matxa-TTS you need to compile the provided espeak-ng with the Catalan phonemizer:
 ```bash
 git clone https://github.com/projecte-aina/espeak-ng.git
 
@@ -97,8 +99,8 @@ pip install -e .
 
 #### PyTorch
 
-Speech end-to-end inference can be done together with **Catalan Matcha-TTS**. 
-Both models (Catalan Matcha-TTS and Vocos) are loaded remotely from the HF hub.  
+Speech end-to-end inference can be done together with **Catalan Matxa-TTS**. 
+Both models (Catalan Matxa-TTS and alVoCat) are loaded remotely from the HF hub.  
 
 First, export the following environment variables to include the installed espeak-ng version:
 
@@ -142,7 +144,7 @@ The model was trained on a **Multiaccent Catalan** speech dataset
 
 ### Training procedure
 
-***Multiaccent Catalan Matcha-TTS*** was finetuned from a catalan central [multispeaker checkpoint](https://huggingface.co/BSC-LT/matcha-tts-cat-multispeaker), 
+***Matxa Multiaccent Catalan*** was finetuned from a catalan central [multispeaker checkpoint](https://huggingface.co/BSC-LT/matcha-tts-cat-multispeaker), that was trained on 28 hours of data from multiple speakers.
 
 The embedding layer was initialized with the number of catalan speakers per accent (2) and the original hyperparameters were kept.
 
@@ -209,4 +211,4 @@ the voice artists. For further information, contact <langtech@bsc.es> and <lafre
 This work has been promoted and financed by the Generalitat de Catalunya through the [Aina project](https://projecteaina.cat/).
 
 Part of the training of the model was possible thanks to the compute time given by Galician Supercomputing Center CESGA
-([Centro de Supercomputación de Galicia](https://www.cesga.es/)), and also by [Barcelona Supercomputing Center](https://www.bsc.es/) in MareNostrum 5.
+([Centro de Supercomputación de Galicia](https://www.cesga.es/)), and also by [Barcelona Supercomputing Center](https://www.bsc.es/) in MareNostrum 5.