Update README.md
Browse files
README.md
CHANGED
@@ -6,4 +6,8 @@ language:
|
|
6 |
---
|
7 |
### Model Description:
|
8 |
|
9 |
-
This is the wav2vec2-base model pre-trained
|
|
|
|
|
|
|
|
|
|
6 |
---
|
7 |
### Model Description:
|
8 |
|
9 |
+
This is the wav2vec2-base model being pre-trained on the My Science Tutor (MyST) dataset (from [LDC](https://catalog.ldc.upenn.edu/LDC2021S05)).
|
10 |
+
|
11 |
+
The pertaining is done by using [fairseq](https://github.com/facebookresearch/fairseq/blob/main/examples/wav2vec/README.md) (wav2vec2_base_librispeech config).
|
12 |
+
|
13 |
+
The converge checkpoint is converted from PyTorch model to Hugging Face model by using a modified version of [convertor script](https://github.com/huggingface/transformers/blob/main/src/transformers/models/wav2vec2/convert_wav2vec2_original_pytorch_checkpoint_to_pytorch.py) offered by Huggingface
|