projecte-aina
/

stt-ca-citrinet-512

Automatic Speech Recognition

Model card Files Files and versions Community

angel-poc commited on Dec 9, 2022

Commit

e61ceb4

·

1 Parent(s): 0176960

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -79,7 +79,7 @@ print(transcriptions)
 ## Training
 ### Data preparation
-We have processed [Common Voice 11.0](https://commonvoice.mozilla.org/en/datasets) using the NeMo toolkit. We used [get_commonvoice_data.py](https://github.com/NVIDIA/NeMo/blob/main/scripts/dataset_processing/get_commonvoice_data.py) to process the manifests and made posterior data cleaning.
 After cleaning the dataset and normalizing the `ñ` character to `ny`, we have used the following charset to create the final NeMo manifests for training.
 ```python

 ## Training
 ### Data preparation
+We have processed [Common Voice 11.0](https://commonvoice.mozilla.org/en/datasets) using the NeMo toolkit. We used [get_commonvoice_data.py](https://github.com/NVIDIA/NeMo/blob/main/scripts/dataset_processing/get_commonvoice_data.py) to process the manifests and made a subsequent data cleaning step.
 After cleaning the dataset and normalizing the `ñ` character to `ny`, we have used the following charset to create the final NeMo manifests for training.
 ```python