Matthijs commited on
Commit
ff0047d
β€’
1 Parent(s): bbb7e65

add link to fine-tuning example notebook

Browse files
Files changed (1) hide show
  1. app.py +2 -0
app.py CHANGED
@@ -68,6 +68,8 @@ SpeechT5 can be fine-tuned for different speech tasks. This space demonstrates t
68
  See also the <a href="https://huggingface.co/spaces/Matthijs/speecht5-asr-demo">speech recognition (ASR) demo</a>
69
  and the <a href="https://huggingface.co/spaces/Matthijs/speecht5-vc-demo">voice conversion demo</a>.
70
 
 
 
71
  <b>How to use:</b> Enter some English text and choose a speaker. The output is a mel spectrogram, which is converted to a mono 16 kHz waveform by the
72
  HiFi-GAN vocoder. Because the model always applies random dropout, each attempt will give slightly different results.
73
  The <em>Surprise Me!</em> option creates a completely randomized speaker.
 
68
  See also the <a href="https://huggingface.co/spaces/Matthijs/speecht5-asr-demo">speech recognition (ASR) demo</a>
69
  and the <a href="https://huggingface.co/spaces/Matthijs/speecht5-vc-demo">voice conversion demo</a>.
70
 
71
+ Refer to <a href="https://colab.research.google.com/drive/1i7I5pzBcU3WDFarDnzweIj4-sVVoIUFJ">this Colab notebook</a> to learn how to fine-tune the SpeechT5 TTS model on your own dataset or language.
72
+
73
  <b>How to use:</b> Enter some English text and choose a speaker. The output is a mel spectrogram, which is converted to a mono 16 kHz waveform by the
74
  HiFi-GAN vocoder. Because the model always applies random dropout, each attempt will give slightly different results.
75
  The <em>Surprise Me!</em> option creates a completely randomized speaker.