Update README.md

README.md

@@ -147,18 +147,6 @@ model-index:
 This model transcribes speech in lower case English alphabet along with spaces and apostrophes.
 It is a "large" versions of Conformer-CTC (around 120M parameters) model.  
 
-## NVIDIA Riva: Deployment
-
-For the best real-time accuracy, latency, and throughput, deploy the model with [NVIDIA Riva], an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, at the edge, and embedded. 
-
-Additionally, Riva provides: 
-
-* World-class out-of-the-box accuracy for the most common languages with model checkpoints trained on proprietary data with hundreds of thousands of GPU-compute hours 
-* Best in class accuracy via customization with run-time word boosting (e.g., brand and product names), acoustic model training, language model training, and inverse text normalization customizations 
-* Streaming speech recognition, Kubernetes compatible scaling, and Enterprise-grade support 
-
-Check out [Riva live demo](https://developer.nvidia.com/riva#demos). 
-
 ## NVIDIA NeMo: Training
 
 To train, fine-tune or play with the model you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed latest Pytorch version.
@@ -203,6 +191,18 @@ This model accepts 16000 KHz Mono-channel Audio (wav files) as input.
 
 This model provides transcribed speech as a string for a given audio sample.
 
+## NVIDIA Riva: Deployment
+
+For the best real-time accuracy, latency, and throughput, deploy the model with [NVIDIA Riva], an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, at the edge, and embedded. 
+
+Additionally, Riva provides: 
+
+* World-class out-of-the-box accuracy for the most common languages with model checkpoints trained on proprietary data with hundreds of thousands of GPU-compute hours 
+* Best in class accuracy via customization with run-time word boosting (e.g., brand and product names), acoustic model training, language model training, and inverse text normalization customizations 
+* Streaming speech recognition, Kubernetes compatible scaling, and Enterprise-grade support 
+
+Check out [Riva live demo](https://developer.nvidia.com/riva#demos). 
+
 ## Model Architecture
 
 Conformer-CTC model is a non-autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses CTC loss/decoding instead of Transducer. You may find more info on the detail of this model here: [Conformer-CTC Model](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html).