Update README.md
Browse files
README.md
CHANGED
@@ -146,6 +146,14 @@ model-index:
|
|
146 |
|
147 |
This is a "large" versions of Conformer-CTC (around 120M parameters) trained on NeMo ASRSet with around 16000 hours of english speech. The model transcribes speech in lower case english alphabet along with spaces and apostrophes.
|
148 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
149 |
## NVIDIA NeMo
|
150 |
|
151 |
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.
|
@@ -157,14 +165,6 @@ pip install nemo_toolkit['all']
|
|
157 |
|
158 |
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.
|
159 |
|
160 |
-
## Deployment in Production
|
161 |
-
|
162 |
-
This model can be efficiently deployed with [NVIDIA Riva](https://developer.nvidia.com/riva) on premises or with cloud providers.
|
163 |
-
Additionally with RIVA you get:
|
164 |
-
* streaming speech recognition mode
|
165 |
-
* ability to boost specific words (e.g. brand and product names)
|
166 |
-
* Conformer checkpoints trained on proprietary data
|
167 |
-
|
168 |
### Automatically instantiate the model
|
169 |
|
170 |
```python
|
|
|
146 |
|
147 |
This is a "large" versions of Conformer-CTC (around 120M parameters) trained on NeMo ASRSet with around 16000 hours of english speech. The model transcribes speech in lower case english alphabet along with spaces and apostrophes.
|
148 |
|
149 |
+
## Deployment in Production
|
150 |
+
|
151 |
+
This model can be efficiently deployed with [NVIDIA Riva](https://developer.nvidia.com/riva) on premises or with cloud providers.
|
152 |
+
Additionally with RIVA you get:
|
153 |
+
* streaming speech recognition mode
|
154 |
+
* ability to boost specific words (e.g. brand and product names)
|
155 |
+
* Conformer checkpoints trained on proprietary data
|
156 |
+
|
157 |
## NVIDIA NeMo
|
158 |
|
159 |
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.
|
|
|
165 |
|
166 |
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.
|
167 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
168 |
### Automatically instantiate the model
|
169 |
|
170 |
```python
|