azalea/CLAP
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Benjamin Elizalde
2023-10-03 14:58:38 -07:00
committed by GitHub
parent cf0e497e03
commit 03703c0e91
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+4 -2
View File
@@ -27,10 +27,12 @@ _clapcap_ is the audio captioning model that uses the 2023 encoders.
## Usage ## Usage
In `CLAP\src\`:
- Zero-Shot Classification and Retrieval - Zero-Shot Classification and Retrieval
```python ```python
# Load model (Choose between versions '2022' or '2023') # Load model (Choose between versions '2022' or '2023')
from src import CLAP from CLAPWrapper import CLAPWrapper as CLAP
clap_model = CLAP("<PATH TO WEIGHTS>", version = '2023', use_cuda=False) clap_model = CLAP("<PATH TO WEIGHTS>", version = '2023', use_cuda=False)
@@ -47,7 +49,7 @@ similarities = clap_model.compute_similarity(audio_embeddings, text_embeddings)
- Audio Captioning - Audio Captioning
```python ```python
# Load model (Choose version 'clapcap') # Load model (Choose version 'clapcap')
from src import CLAP from CLAPWrapper import CLAPWrapper as CLAP
clap_model = CLAP("<PATH TO WEIGHTS>", version = 'clapcap', use_cuda=False) clap_model = CLAP("<PATH TO WEIGHTS>", version = 'clapcap', use_cuda=False)