smajumdar94 commited on
Commit
bc1c969
1 Parent(s): de6875d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -123,7 +123,7 @@ This model provides transcribed speech as a string for a given audio sample.
123
 
124
  ## Model Architecture
125
 
126
- FastConformer is an optimized version of the Conformer model [1] with 8x depthwise-separable convolutional downsampling. The model is trained in a multitask setup with joint Transducer and CTC decoder loss. You may find more information on the details of FastConformer here: [Fast-Conformer Model](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer) and about Hybrid Transducer-CTC training here: [Hybrid Transducer-CTC](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#hybrid-transducer-ctc).
127
 
128
  ## Training
129
 
@@ -173,7 +173,7 @@ Although this model isn’t supported yet by Riva, the [list of supported models
173
  Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
174
 
175
  ## References
176
- [1] [Conformer: Convolution-augmented Transformer for Speech Recognition](https://arxiv.org/abs/2005.08100)
177
 
178
  [2] [Google Sentencepiece Tokenizer](https://github.com/google/sentencepiece)
179
 
 
123
 
124
  ## Model Architecture
125
 
126
+ FastConformer [1] is an optimized version of the Conformer model with 8x depthwise-separable convolutional downsampling. The model is trained in a multitask setup with joint Transducer and CTC decoder loss. You may find more information on the details of FastConformer here: [Fast-Conformer Model](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer) and about Hybrid Transducer-CTC training here: [Hybrid Transducer-CTC](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#hybrid-transducer-ctc).
127
 
128
  ## Training
129
 
 
173
  Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
174
 
175
  ## References
176
+ [1] [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://arxiv.org/abs/2305.05084)
177
 
178
  [2] [Google Sentencepiece Tokenizer](https://github.com/google/sentencepiece)
179