lucio commited on
Commit
63869be
1 Parent(s): 6a0c5d4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -28,7 +28,7 @@ model-index:
28
 
29
  # Wav2Vec2-Large-XLSR-53-rw
30
 
31
- Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Kinyarwanda using the [Common Voice](https://huggingface.co/datasets/common_voice) dataset, using about 20% of the training data (limited to utterances without downvotes and shorter than 9.5 seconds), and validated on 2048 utterances from the validation set.
32
  When using this model, make sure that your speech input is sampled at 16kHz.
33
 
34
  ## Usage
 
28
 
29
  # Wav2Vec2-Large-XLSR-53-rw
30
 
31
+ Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Kinyarwanda using the [Common Voice](https://huggingface.co/datasets/common_voice) dataset, using about 20% of the training data (limited to utterances without downvotes and shorter than 9.5 seconds), and validated on 2048 utterances from the validation set. In contrast to the [lucio/wav2vec2-large-xlsr-kinyarwanda-apostrophied](https://huggingface.co/lucio/wav2vec2-large-xlsr-kinyarwanda-apostrophied) model, which predicts the apostrophes that mark contractions of pronouns with vowel-initial words, this model does not predict any punctuation.
32
  When using this model, make sure that your speech input is sampled at 16kHz.
33
 
34
  ## Usage