BUT-FIT
/

wav2vec2-base_bart-base_voxpopuli-en

Automatic Speech Recognition

speech-encoder-decoder

Generated from Trainer

Model card Files Files and versions

matejhornik commited on May 17

Commit

0b3f0ad

·

verified ·

1 Parent(s): ce588ec

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -56,7 +56,7 @@ metrics:
 This repository contains the checkpoint for a `SpeechEncoderDecoderModel` fine-tuned for Automatic Speech Recognition (ASR) on the English portion of the VoxPopuli dataset. This model achieved the **best Word Error Rate (WER) of 8.85% on the VoxPopuli English test set** within the experimental framework of the Master's thesis "Effective Training of Neural Networks for Automatic Speech Recognition" by Matej Horník.
-The model leverages a pre-trained **Wav2Vec2 (Base)** encoder (`facebook/wav2vec2-base-en-voxpopuli-v2`) and a pre-trained **BART (Base)** decoder (`facebook/bart-base`), connected via convolutional adapter layers.
 ## Thesis Context

 This repository contains the checkpoint for a `SpeechEncoderDecoderModel` fine-tuned for Automatic Speech Recognition (ASR) on the English portion of the VoxPopuli dataset. This model achieved the **best Word Error Rate (WER) of 8.85% on the VoxPopuli English test set** within the experimental framework of the Master's thesis "Effective Training of Neural Networks for Automatic Speech Recognition" by Matej Horník.
+The model leverages a pre-trained **Wav2Vec2 (Base)** encoder [`facebook/wav2vec2-base-en-voxpopuli-v2`](https://huggingface.co/facebook/wav2vec2-base-en-voxpopuli-v2) and a pre-trained **BART (Base)** decoder [`facebook/bart-base`](https://huggingface.co/facebook/bart-base).
 ## Thesis Context