Spaces:

projecte-aina
/

matxa-alvocat-tts-ca

Running

AlexK-PL commited on Jun 13

Commit

efd7fee

•

1 Parent(s): e576287

Update about.md

Files changed (1) hide show

about.md CHANGED Viewed

@@ -226,7 +226,7 @@ This version is tailored for the Catalan language, as it was trained only on Cat
 The original Matcha-TTS model excels in English, but to adapt it to Catalan, we have carried out a multi-stage process.
 First, we fine-tuned the English to Central Catalan model by creating a Matxa-base, using a 100h subset of the CommonVoice v.16 Catalan database.
-The selection of this small set of samples has been performed automatically using the UTMOS system, a predictor of values of the metric Mean Opinion Score (MOS) a score that is usually set by humans according to their subjective perception of the quality of the speech.
 Then we further fine-tuned the single accent Catalan Matxa-based model with the soon to be published LaFrescat dataset that has 3.5 hours of recordings for four dialectal variants:

 The original Matcha-TTS model excels in English, but to adapt it to Catalan, we have carried out a multi-stage process.
 First, we fine-tuned the English to Central Catalan model by creating a Matxa-base, using a 100h subset of the CommonVoice v.16 Catalan database.
+The selection of this small set of samples has been performed automatically using the UTMOS system, a predictor of values of the metric Mean Opinion Score (MOS) a score usually set by human evaluators according to their subjective perception of speech quality.
 Then we further fine-tuned the single accent Catalan Matxa-based model with the soon to be published LaFrescat dataset that has 3.5 hours of recordings for four dialectal variants: