nljubesi commited on
Commit
f96ad24
1 Parent(s): 814db04

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ widget:
18
 
19
  This model is based on the [facebook/wav2vec2-xls-r-300m model](https://huggingface.co/facebook/wav2vec2-xls-r-300m) and was fine-tuned with 72 hours of recordings and transcripts from the Croatian parliament. This training dataset is an early result of the second iteration of the [ParlaMint project](https://www.clarin.eu/content/parlamint-towards-comparable-parliamentary-corpora) inside which the dataset will be extended and published under the name ParlaSpeech-HR and an open licence.
20
 
21
- The efforts resulting in this model were coordinated by Nikola Ljubešić, the rough manual data alignment was performed by Ivo-Pavao Jazbec, the method for fine automatic data alignment from [Plüss et al.](https://arxiv.org/abs/2010.02810) was applied by Vuk Batanović and Lenka Bajčetić, the transcripts were normalised with a tool by Danijel Korzinek, while the final modelling was performed by Peter Rupnik.
22
 
23
  Initial evaluation on partially noisy data showed the model to achieve a word error rate of 13.68% and a character error rate of 4.56%.
24
 
 
18
 
19
  This model is based on the [facebook/wav2vec2-xls-r-300m model](https://huggingface.co/facebook/wav2vec2-xls-r-300m) and was fine-tuned with 72 hours of recordings and transcripts from the Croatian parliament. This training dataset is an early result of the second iteration of the [ParlaMint project](https://www.clarin.eu/content/parlamint-towards-comparable-parliamentary-corpora) inside which the dataset will be extended and published under the name ParlaSpeech-HR and an open licence.
20
 
21
+ The efforts resulting in this model were coordinated by Nikola Ljubešić, the rough manual data alignment was performed by Ivo-Pavao Jazbec, the method for fine automatic data alignment from [Plüss et al.](https://arxiv.org/abs/2010.02810) was applied by Vuk Batanović and Lenka Bajčetić, the transcripts were normalised by Danijel Korzinek, while the final modelling was performed by Peter Rupnik.
22
 
23
  Initial evaluation on partially noisy data showed the model to achieve a word error rate of 13.68% and a character error rate of 4.56%.
24