<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="ca">
	<id>http://wiki.joanillo.org/index.php?action=history&amp;feed=atom&amp;title=TTS%3A_S%C3%ADntesi_de_veu</id>
	<title>TTS: Síntesi de veu - Historial de revisió</title>
	<link rel="self" type="application/atom+xml" href="http://wiki.joanillo.org/index.php?action=history&amp;feed=atom&amp;title=TTS%3A_S%C3%ADntesi_de_veu"/>
	<link rel="alternate" type="text/html" href="http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;action=history"/>
	<updated>2026-10-10T23:27:40Z</updated>
	<subtitle>Historial de revisió per a aquesta pàgina del wiki</subtitle>
	<generator>MediaWiki 1.34.2</generator>
	<entry>
		<id>http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299242&amp;oldid=prev</id>
		<title>Joan: /* Síntesi de veu amb vits */</title>
		<link rel="alternate" type="text/html" href="http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299242&amp;oldid=prev"/>
		<updated>2026-10-10T23:14:37Z</updated>

		<summary type="html">&lt;p&gt;&lt;span dir=&quot;auto&quot;&gt;&lt;span class=&quot;autocomment&quot;&gt;Síntesi de veu amb vits&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;
&lt;table class=&quot;diff diff-contentalign-left&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;ca&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #222; text-align: center;&quot;&gt;← Versió més antiga&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #222; text-align: center;&quot;&gt;Revisió del 23:14, 10 oct 2026&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l506&quot; &gt;Línia 506:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Línia 506:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;'''NOTA''': com que ja tenia aquesta part funcionant, ara vaig voler continuar amb el RVC per fer clonació. Però les millors proves de clonació les he aconseguit amb el model de síntesi del Matxa v2, que no necessita espeak-ng.&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;'''NOTA''': com que ja tenia aquesta part funcionant, ara vaig voler continuar amb el RVC per fer clonació. Però les millors proves de clonació les he aconseguit amb el model de síntesi del Matxa v2, que no necessita espeak-ng.&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;===Les veus només són en català central===&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Amb el script prova.py m'he generat les veus dels 840 speakers, i després de mirar els 30 primers, tots es corresponen de moment a català central. Espero trobar entre les veus accent de Lleida, de València i de Mallorca, però no els veig. Estic fent alguna cosa malament, espero trobar diversitat dialectal&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;No estàs fent res malament. És una limitació del model: amb aquest model no trobaràs accents diferents del central, i és normal que no aparegui la diversitat que busques. Per què totes les veus sonen a català central?&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;El model no llegeix el text directament. Primer el converteix en fonemes amb '''espeak-ng''' configurat amb l'idioma ca, i aquesta transcripció segueix la pronúncia del català central. Per tant, trets com la reducció vocàlica (a/e àtones → [ə]) o la -r final muda ja vénen decidits abans d'arribar a la veu.&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;El parlant escollit només canvia el timbre, el to i una mica la prosòdia. Encara que el parlant original fos de València o de Mallorca, el model li fa pronunciar els fonemes centrals, i el resultat és una veu valenciana &amp;quot;llegint en central&amp;quot;. A més, a Common Voice els parlants de català central són clarament majoritaris, cosa que reforça aquest biaix.&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;L'alternativa: un model multidialectal&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;El BSC ha publicat Matxa, un model pensat precisament per això. Funciona juntament amb el vocoder alVoCat i genera veu en quatre dialectes: balear, central, nord-occidental i valencià. Per tant, està basat en grafemes i no necessita el espeak-ng.&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;==Síntesi de veu amb Matxa v2==&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;L'alternativa: un model multidialectal&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;El BSC ha publicat Matxa, un model pensat precisament per això. Funciona juntament amb el vocoder alVoCat i genera veu en quatre dialectes: balear, central, nord-occidental i valencià. Té dues veus per dialecte: &lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&amp;lt;pre&amp;gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Accent	Veus (speaker_id)	Cleaner&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Balear	quim (0), olga (1)	catalan_balear_cleaners&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Central	grau (2), elia (3)	catalan_cleaners&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Nord-occidental (Lleida)	pere (4), emma (5)	catalan_occidental_cleaners&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Valencià	lluc (6), gina (7)	catalan_valencia_cleaners&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&amp;lt;/pre&amp;gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Podem escoltar totes les veus aquí:&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;* https://huggingface.co/spaces/projecte-aina/matxa-alvocat-tts-ca&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;{{Autor}}, setembre 2026&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;{{Autor}}, setembre 2026&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Joan</name></author>
		
	</entry>
	<entry>
		<id>http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299240&amp;oldid=prev</id>
		<title>Joan: /* Síntesi de veu amb vits */</title>
		<link rel="alternate" type="text/html" href="http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299240&amp;oldid=prev"/>
		<updated>2026-10-10T22:20:39Z</updated>

		<summary type="html">&lt;p&gt;&lt;span dir=&quot;auto&quot;&gt;&lt;span class=&quot;autocomment&quot;&gt;Síntesi de veu amb vits&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;
&lt;table class=&quot;diff diff-contentalign-left&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;ca&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #222; text-align: center;&quot;&gt;← Versió més antiga&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #222; text-align: center;&quot;&gt;Revisió del 22:20, 10 oct 2026&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l504&quot; &gt;Línia 504:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Línia 504:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* https://huggingface.co/projecte-aina/tts-ca-coqui-vits-multispeaker&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* https://huggingface.co/projecte-aina/tts-ca-coqui-vits-multispeaker&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* https://huggingface.co/spaces/softcatala/comparativa-tts-catala&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* https://huggingface.co/spaces/softcatala/comparativa-tts-catala&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td colspan=&quot;2&quot;&gt; &lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;'''NOTA''': com que ja tenia aquesta part funcionant, ara vaig voler continuar amb el RVC per fer clonació. Però les millors proves de clonació les he aconseguit amb el model de síntesi del Matxa v2, que no necessita espeak-ng.&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;{{Autor}}, setembre 2026&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;{{Autor}}, setembre 2026&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Joan</name></author>
		
	</entry>
	<entry>
		<id>http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299239&amp;oldid=prev</id>
		<title>Joan: /* 2a prova: model VITS */</title>
		<link rel="alternate" type="text/html" href="http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299239&amp;oldid=prev"/>
		<updated>2026-10-10T22:01:01Z</updated>

		<summary type="html">&lt;p&gt;&lt;span dir=&quot;auto&quot;&gt;&lt;span class=&quot;autocomment&quot;&gt;2a prova: model VITS&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;
&lt;table class=&quot;diff diff-contentalign-left&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;ca&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #222; text-align: center;&quot;&gt;← Versió més antiga&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #222; text-align: center;&quot;&gt;Revisió del 22:01, 10 oct 2026&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l310&quot; &gt;Línia 310:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Línia 310:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;  5  ca-va           --/M      Catalan_(Valencian) roa/ca-va  &lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;  5  ca-va           --/M      Catalan_(Valencian) roa/ca-va  &lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;lt;/pre&amp;gt;&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;lt;/pre&amp;gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt;−&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt; &lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt;+&lt;/td&gt;&lt;td style=&quot;color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&lt;ins class=&quot;diffchange diffchange-inline&quot;&gt;==Síntesi de veu amb vits==&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;lt;pre&amp;gt;&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;&amp;lt;pre&amp;gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;python -c &amp;quot;from TTS.api import TTS; print('OK')&amp;quot;&lt;/div&gt;&lt;/td&gt;&lt;td class='diff-marker'&gt; &lt;/td&gt;&lt;td style=&quot;background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;python -c &amp;quot;from TTS.api import TTS; print('OK')&amp;quot;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>Joan</name></author>
		
	</entry>
	<entry>
		<id>http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299238&amp;oldid=prev</id>
		<title>Joan: /* 2a prova: model VITS */</title>
		<link rel="alternate" type="text/html" href="http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299238&amp;oldid=prev"/>
		<updated>2026-10-10T21:56:20Z</updated>

		<summary type="html">&lt;p&gt;&lt;span dir=&quot;auto&quot;&gt;&lt;span class=&quot;autocomment&quot;&gt;2a prova: model VITS&lt;/span&gt;&lt;/span&gt;&lt;/p&gt;
&lt;a href=&quot;http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;amp;diff=299238&amp;amp;oldid=299237&quot;&gt;Mostra els canvis&lt;/a&gt;</summary>
		<author><name>Joan</name></author>
		
	</entry>
	<entry>
		<id>http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299237&amp;oldid=prev</id>
		<title>Joan a 21:19, 10 oct 2026</title>
		<link rel="alternate" type="text/html" href="http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299237&amp;oldid=prev"/>
		<updated>2026-10-10T21:19:58Z</updated>

		<summary type="html">&lt;p&gt;&lt;/p&gt;
&lt;a href=&quot;http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;amp;diff=299237&amp;amp;oldid=299236&quot;&gt;Mostra els canvis&lt;/a&gt;</summary>
		<author><name>Joan</name></author>
		
	</entry>
	<entry>
		<id>http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299236&amp;oldid=prev</id>
		<title>Joan: Es crea la pàgina amb «__TOC__  =1a prova: F5-TTS, no funciona=  (no acaba de funcionar, resultats inconsistents)  *https://chatgpt.com/c/6ab042c5-4344-83eb-90bb-83cad23ab322  (m'he fet un l...».</title>
		<link rel="alternate" type="text/html" href="http://wiki.joanillo.org/index.php?title=TTS:_S%C3%ADntesi_de_veu&amp;diff=299236&amp;oldid=prev"/>
		<updated>2026-10-10T21:09:04Z</updated>

		<summary type="html">&lt;p&gt;Es crea la pàgina amb «__TOC__  =1a prova: F5-TTS, no funciona=  (no acaba de funcionar, resultats inconsistents)  *https://chatgpt.com/c/6ab042c5-4344-83eb-90bb-83cad23ab322  (m&amp;#039;he fet un l...».&lt;/p&gt;
&lt;p&gt;&lt;b&gt;Pàgina nova&lt;/b&gt;&lt;/p&gt;&lt;div&gt;__TOC__&lt;br /&gt;
&lt;br /&gt;
=1a prova: F5-TTS, no funciona=&lt;br /&gt;
&lt;br /&gt;
(no acaba de funcionar, resultats inconsistents)&lt;br /&gt;
&lt;br /&gt;
*https://chatgpt.com/c/6ab042c5-4344-83eb-90bb-83cad23ab322&lt;br /&gt;
&lt;br /&gt;
(m'he fet un lio amb el XTTS-v2 i la instal·lació de Coqui TTS)&lt;br /&gt;
&lt;br /&gt;
prompt: &amp;quot;vull fer clonació i síntesi de veu en català amb F5-TTS. Tinc una RTX5060 Ti 16GB.&amp;quot;&lt;br /&gt;
&lt;br /&gt;
Per català, però, hi ha un punt important: el model base de F5-TTS no és específicament un model català, així que la qualitat de pronunciació catalana dependrà molt del text, del model/checkpoint i de l'àudio de referència. Si vols qualitat alta i consistent en català, podem plantejar també fine-tuning.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
mkdir -p F5-TTS&lt;br /&gt;
cd F5-TTS&lt;br /&gt;
python3 -m venv .venv&lt;br /&gt;
source .venv/bin/activate&lt;br /&gt;
python -m pip install --upgrade pip setuptools wheel&lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
3. Instal·la PyTorch&lt;br /&gt;
El repositori actual de F5-TTS documenta PyTorch amb CUDA 12.8, i PyTorch publica wheels específiques cu128.&lt;br /&gt;
&lt;br /&gt;
Jo tinc CUDA 13.2, però no passa res&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
pip install torch==2.8.0+cu128 torchaudio==2.8.0+cu128 \&lt;br /&gt;
    --extra-index-url https://download.pytorch.org/whl/cu128&lt;br /&gt;
&lt;br /&gt;
$ python3&lt;br /&gt;
import torch&lt;br /&gt;
&lt;br /&gt;
print(&amp;quot;PyTorch:&amp;quot;, torch.__version__)&lt;br /&gt;
print(&amp;quot;CUDA:&amp;quot;, torch.version.cuda)&lt;br /&gt;
print(&amp;quot;CUDA disponible:&amp;quot;, torch.cuda.is_available())&lt;br /&gt;
print(&amp;quot;GPU:&amp;quot;, torch.cuda.get_device_name(0))&lt;br /&gt;
print(&amp;quot;Compute capability:&amp;quot;, torch.cuda.get_device_capability(0))&lt;br /&gt;
&lt;br /&gt;
PyTorch: 2.8.0+cu128&lt;br /&gt;
CUDA: 12.8&lt;br /&gt;
CUDA disponible: True&lt;br /&gt;
GPU: NVIDIA GeForce RTX 5060 Ti&lt;br /&gt;
Compute capability: (12, 0)&lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
4. Instal·la F5-TTS&lt;br /&gt;
&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
git clone https://github.com/SWivid/F5-TTS.git&lt;br /&gt;
&lt;br /&gt;
cd F5-TTS&lt;br /&gt;
pip install -e .&lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
ara el meu directori de treball és ~/F5-TTS/F5-TTS. No confondre el primer amb el segon.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
$ f5-tts_infer-cli --help&lt;br /&gt;
$ f5-tts_infer-gradio --help -&amp;gt; es descarrega el model&lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
5. Primera prova: interfície web&lt;br /&gt;
&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
$ f5-tts_infer-gradio&lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
Normalment et donarà una adreça local del tipus:&lt;br /&gt;
&lt;br /&gt;
* http://127.0.0.1:7860&lt;br /&gt;
&lt;br /&gt;
Obre-la al navegador.&lt;br /&gt;
&lt;br /&gt;
La interfície de F5-TTS permet fer inferència a partir d'una veu de referència i generar text nou. El projecte actual també disposa de funcionalitats d'inferència per chunks i altres modes.&lt;br /&gt;
&lt;br /&gt;
però jo no estic davant de l'ordinador. I no puc fer:&lt;br /&gt;
&lt;br /&gt;
* http://79.156.157.3:7860&lt;br /&gt;
&lt;br /&gt;
perquè el port 7860 no està obert&lt;br /&gt;
(m'he quedat aquí)&lt;br /&gt;
(...)&lt;br /&gt;
&lt;br /&gt;
Gravo una veu que representa que és de referència, i a partir d'aquesta veu podré fer síntesi.&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
$ arecord -f cd  gravacio.wav&lt;br /&gt;
&lt;br /&gt;
scp gravacio.* joan@192.168.1.184:/home/joan/Baixades&lt;br /&gt;
&lt;br /&gt;
&lt;br /&gt;
$ f5-tts_infer-cli --model F5TTS_Base --ref_audio /home/joan/Baixades/gravacio.wav --ref_text &amp;quot;It was a cold and quiet evening when Emily arrived in the small village of Blackwood. The streets were almost empty, and a thick fog covered the old houses. As she walked towards the house she had recently inherited from her grandmother, she noticed a strange light shining from one of the upstairs windows. Emily stopped and stared at it for a moment. She was certain that the house had been empty for years, so she could not understand who could be inside.&amp;quot; --gen_text &amp;quot;Good morning. This is a simple test of generating an English speech from a text&amp;quot; --output_dir /home/joan/projectes --output_file prova.wav --speed 0.06&lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
&lt;br /&gt;
es genera el fitxer /home/joan/Baixades/prova.wav&lt;br /&gt;
&lt;br /&gt;
NOTA: recordem que en el portàtil tinc un punt de muntatge a /home/joan/projectes en el servidor.&lt;br /&gt;
&lt;br /&gt;
&amp;lt;pre&amp;gt;&lt;br /&gt;
$ find ~/.cache/gface -type d -iname &amp;quot;*F5*&amp;quot; 2&amp;gt;/dev/null&lt;br /&gt;
/home/joan/.cache/huggingface/hub/models--SWivid--F5-TTS&lt;br /&gt;
/home/joan/.cache/huggingface/hub/models--SWivid--F5-TTS/snapshots/84e5a410d9cead4de2f847e7c9369a6440bdfaca/F5TTS_v1_Base&lt;br /&gt;
/home/joan/.cache/huggingface/hub/models--SWivid--F5-TTS/snapshots/84e5a410d9cead4de2f847e7c9369a6440bdfaca/F5TTS_Base&lt;br /&gt;
/home/joan/.cache/huggingface/hub/.locks/models--SWivid--F5-TTS&lt;br /&gt;
&lt;br /&gt;
$ f5-tts_infer-cli --model F5TTS_v1_Base --ref_audio /home/joan/Baixades/gravacio.wav --ref_text &amp;quot;It was a cold and quiet evening when Emily arrived in the small village of Blackwood. The streets were almost empty, and a thick fog covered the old houses. As she walked towards the house she had recently inherited from her grandmother, she noticed a strange light shining from one of the upstairs windows. Emily stopped and stared at it for a moment. She was certain that the house had been empty for years, so she could not understand who could be inside.&amp;quot; --gen_text &amp;quot;Good morning. This is a simple test of generating an English speech from a text&amp;quot; --output_dir /home/joan/projectes --output_file prova2.wav --speed 0.06&lt;br /&gt;
&lt;br /&gt;
$ f5-tts_infer-cli --model F5TTS_Base --ref_audio /home/joan/projectes/gravacio2.wav --ref_text &amp;quot;It was a cold and quiet evening when Emily arrived in the small village of Blackwood.&amp;quot; --gen_text &amp;quot;Good morning. This is a simple test of generating an English speech from a text&amp;quot; --output_dir /home/joan/projectes --output_file prova.wav --speed 0.06&lt;br /&gt;
&amp;lt;/pre&amp;gt;&lt;br /&gt;
No m'acaba de sortir. Obtinc uns resultats en anglès bastant inconsistents, i en català no ho aconseguiré.&lt;br /&gt;
&lt;br /&gt;
{{Autor}}, setembre 2026&lt;/div&gt;</summary>
		<author><name>Joan</name></author>
		
	</entry>
</feed>