Add reference to the cache-aware paper. (#2)

- Add reference to the cache-aware paper. (7a4ebdeb9844203deb5ceea1631603a3ed32c949)


Co-authored-by: Vahid Noroozi <vnoroozi@users.noreply.huggingface.co>

README.md

@@ -11,9 +11,9 @@ datasets:
 - National-Singapore-Corpus-Part-1
 - National-Singapore-Corpus-Part-6
 - vctk
-- VoxPopuli-(EN)
-- Europarl-ASR-(EN)
-- Multilingual-LibriSpeech-(2000-hours)
+- VoxPopuli-EN
+- Europarl-ASR-EN
+- Multilingual-LibriSpeech-2000hours
 - mozilla-foundation/common_voice_8_0
 - MLCommons/peoples_speech
 thumbnail: null
@@ -66,19 +66,19 @@ img {
 
 This collection contains large-size versions of cache-aware FastConformer-Hybrid (around 114M parameters) with multiple look-ahead support, trained on a large scale english speech. 
 These models are trained for streaming ASR, which be used for streaming applications with a variety of latencies (0ms, 80ms, 480s, 1040ms). 
-These are the worst latency and average latency of the model for each case would be half of these numbers.
+These are the worst latency and average latency of the model for each case would be half of these numbers. You may find more detail and evalution results [here](https://arxiv.org/abs/2312.17279) [5].
 
 
 ## Model Architecture
 
-These models are cache-aware versions of Hybrid FastConfomer which are trained for streaming ASR. You may find more info on cache-aware models here: [Cache-aware Streaming Conformer](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#cache-aware-streaming-conformer).
+These models are cache-aware versions of Hybrid FastConfomer which are trained for streaming ASR. You may find more info on cache-aware models here: [Cache-aware Streaming Conformer](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#cache-aware-streaming-conformer) [5].
 The models are trained with multiple look-aheads which makes the model to be able to support different latencies. 
 To learn on how to switch between different look-ahead, you may read the documentation on the cache-aware models.
 
 FastConformer [4] is an optimized version of the Conformer model [1], and 
 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). 
 
-The model is trained in a multitask setup with joint Transducer and CTC decoder loss. You can find more 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). 
+The model is trained in a multitask setup with joint Transducer and CTC decoder loss [5]. You can find more 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). 
 You may also find more on how to switch between the Transducer and CTC decoders in the documentation.
 
  
@@ -226,3 +226,6 @@ Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
 [3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
 
 [4] [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://arxiv.org/abs/2305.05084)
+
+[5] [Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognition
+](https://arxiv.org/abs/2312.17279)