smajumdar94
commited on
Commit
•
43d18c7
1
Parent(s):
a7ebc39
Update README.md
Browse files
README.md
CHANGED
@@ -147,6 +147,18 @@ model-index:
|
|
147 |
This model transcribes speech in lower case English alphabet along with spaces and apostrophes.
|
148 |
It is a "extra-large" versions of Conformer-Transducer (around 600M parameters) model.
|
149 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
150 |
## NVIDIA NeMo: Training
|
151 |
|
152 |
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.
|
@@ -154,10 +166,6 @@ To train, fine-tune or play with the model you will need to install [NVIDIA NeMo
|
|
154 |
pip install nemo_toolkit['all']
|
155 |
```
|
156 |
|
157 |
-
## NVIDIA Riva: Deployment
|
158 |
-
|
159 |
-
[CTC-based Conformers](https://huggingface.co/nvidia/stt_en_conformer_ctc_large) are supported by Riva today. This model, as well as other RNNT-based models, will be supported by future versions of [NVIDIA Riva](https://developer.nvidia.com/riva).
|
160 |
-
|
161 |
## How to Use this Model
|
162 |
|
163 |
The model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.
|
|
|
147 |
This model transcribes speech in lower case English alphabet along with spaces and apostrophes.
|
148 |
It is a "extra-large" versions of Conformer-Transducer (around 600M parameters) model.
|
149 |
|
150 |
+
## NVIDIA Riva: Deployment
|
151 |
+
|
152 |
+
If you like this and other models from NVIDIA (i.e., CTC-based Conformers) check out [NVIDIA Riva](https://developer.nvidia.com/riva), an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, on edge, and embedded. This model, as well as other RNNT-based models are currently not supported by Riva. You can find the list of models supported by Riva [here](https://docs.nvidia.com/deeplearning/riva/user-guide/docs/reference/models/index.html).
|
153 |
+
|
154 |
+
Additionally, Riva provides:
|
155 |
+
|
156 |
+
* 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
|
157 |
+
* 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
|
158 |
+
* Streaming speech recognition, Kubernetes compatible scaling, and Enterprise-grade support
|
159 |
+
|
160 |
+
Check out [Riva live demo](https://developer.nvidia.com/riva#demos).
|
161 |
+
|
162 |
## NVIDIA NeMo: Training
|
163 |
|
164 |
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.
|
|
|
166 |
pip install nemo_toolkit['all']
|
167 |
```
|
168 |
|
|
|
|
|
|
|
|
|
169 |
## How to Use this Model
|
170 |
|
171 |
The model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.
|