Update README.md
Browse files
README.md
CHANGED
|
@@ -224,6 +224,11 @@ Canary-Qwen is a Speech-Augmented Language Model (SALM) [9] model with FastConfo
|
|
| 224 |
|
| 225 |
To train, fine-tune or transcribe with Canary-Qwen-2.5B, you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo).
|
| 226 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 227 |
## How to Use this Model
|
| 228 |
|
| 229 |
The model is available for use in the NVIDIA NeMo toolkit [6], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.
|
|
|
|
| 224 |
|
| 225 |
To train, fine-tune or transcribe with Canary-Qwen-2.5B, you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo).
|
| 226 |
|
| 227 |
+
```bash
|
| 228 |
+
# Currently requires installing the latest trunk version of NeMo, and PyTorch 2.6+ for FSDP2 support.
|
| 229 |
+
pip install git+https://github.com/NVIDIA/NeMo
|
| 230 |
+
```
|
| 231 |
+
|
| 232 |
## How to Use this Model
|
| 233 |
|
| 234 |
The model is available for use in the NVIDIA NeMo toolkit [6], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.
|