Update README.md

README.md

@@ -67,7 +67,7 @@ under [Additional information](#additional-information).
 ### Installation
 
 Models have been trained using the espeak-ng open source text-to-speech software. 
-The espeak-ng containing the Catalan phonemizer can be found [here](https://github.com/projecte-aina/espeak-ng)
+The main (espeak-ng)[https://github.com/espeak-ng/espeak-ng] now contains the Catalan phonemizer work started [here](https://github.com/projecte-aina/espeak-ng)
 
 Create a virtual environment:
 ```bash
@@ -77,9 +77,9 @@ python -m venv /path/to/venv
 source /path/to/venv/bin/activate
 ```
 
-For training and synthesizing with Catalan Matxa-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 espeak-ng:
 ```bash
-git clone https://github.com/projecte-aina/espeak-ng.git
+git clone https://github.com/espeak-ng/espeak-ng
 
 export PYTHON=/path/to/env/<env_name>/bin/python
 cd /path/to/espeak-ng
@@ -87,10 +87,6 @@ cd /path/to/espeak-ng
 ./configure --prefix=/path/to/espeak-ng
 make
 make install
-
-pip cache purge
-pip install mecab-python3
-pip install unidic-lite
 ```
 Clone the repository:
 
@@ -134,6 +130,25 @@ python3 matcha_vocos_inference.py --output_path=/output/path --text_input="Bon d
 
 ```
 
+Additionally you can choose the speaker id from the following table
+
+```bash
+python3 matcha_vocos_inference.py --output_path=/output/path --text_input="Bon dia Manel, avui anem a la muntanya." --length_scale=0.8 --temperature=0.7 --speaker_id 3
+
+```
+
+| accent | Name | speaker_id |
+|-----------------|------|------------|
+| balear | quim | 0 |
+| balear | olga | 1 |
+| central | grau | 2 |
+| central | elia | 3 |
+| nord-occidental | pere | 4 |
+| nord-occidental | emma | 5 |
+| valencia | lluc | 6 |
+| valencia | gina | 7 |
+
+
 #### ONNX
 
 We also release ONNXs version of the models