Link to dataset

README.md

@@ -29,15 +29,16 @@ language:
 - sw
 - yo
 - wo
-thumbnail: >-
-  https://raw.githubusercontent.com/DanRuta/xVA-Synth/master/assets/x-icon.png
+thumbnail: https://raw.githubusercontent.com/DanRuta/xVA-Synth/master/assets/x-icon.png
 library: xvasynth
 tags:
-  - emotion
-  - audio
-  - text-to-speech
-  - tts
+- emotion
+- audio
+- text-to-speech
+- tts
 pipeline_tag: text-to-speech
+datasets:
+- MikhailT/hifi-tts
 ---
 
 xVASynth's xVAPitch (v3) type of voice models based on NVIDIA HIFI NeMo datasets.
@@ -54,4 +55,4 @@ xVAPitch model referenced Papers:
 - SDP - https://arxiv.org/pdf/2106.06103.pdf
 - Spline Flow - https://arxiv.org/abs/1906.04032
 
-Legal note: Although these datasets are licensed as CC BY 4.0, the base v3 model that these are fine-tuned from, was pre-trained on non-permissive data.
+Legal note: Although these datasets are licensed as CC BY 4.0, the base v3 model that these models are fine-tuned from, was pre-trained on non-permissive data.