Update README.md
Browse files
README.md
CHANGED
|
@@ -30,7 +30,8 @@ datasets:
|
|
| 30 |
|
| 31 |
## Model Architecture
|
| 32 |
|
| 33 |
-
|
|
|
|
| 34 |
[Fast Conformer with Linearly Scalable Attention for Efficient
|
| 35 |
Speech Recognition](https://arxiv.org/abs/2305.05084).
|
| 36 |
|
|
|
|
| 30 |
|
| 31 |
## Model Architecture
|
| 32 |
|
| 33 |
+
This model uses a FastConformer-TDT architecture. FastConformer [1] is an optimized version of the Conformer model with 8x depthwise-separable convolutional downsampling.
|
| 34 |
+
You may find more information on the details of FastConformer here: Fast-Conformer Model.
|
| 35 |
[Fast Conformer with Linearly Scalable Attention for Efficient
|
| 36 |
Speech Recognition](https://arxiv.org/abs/2305.05084).
|
| 37 |
|