Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,11 @@
|
|
| 2 |
|
| 3 |
Copy the github repo, build the spiritlm python package and put models in `checkpoints` folder before running the script. I would suggest to use conda environment for this.
|
| 4 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
```python
|
| 6 |
import gradio as gr
|
| 7 |
from spiritlm.model.spiritlm_model import Spiritlm, OutputModality, GenerationInput, ContentType
|
|
|
|
| 2 |
|
| 3 |
Copy the github repo, build the spiritlm python package and put models in `checkpoints` folder before running the script. I would suggest to use conda environment for this.
|
| 4 |
|
| 5 |
+
You need around 15.5GB of VRAM to run the model with short output length and around 19GB to output 800 tokens.
|
| 6 |
+
|
| 7 |
+
Edit: Audio to audio inference doesn't seem great. Potentially I am tokenizing the audio wrong.
|
| 8 |
+
|
| 9 |
+
|
| 10 |
```python
|
| 11 |
import gradio as gr
|
| 12 |
from spiritlm.model.spiritlm_model import Spiritlm, OutputModality, GenerationInput, ContentType
|