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

[U] Publish pypi

Browse Source
This commit is contained in:
Azalea Gui
2023-10-11 20:06:24 -04:00
parent 9f902c9029
commit 765f9f8864
2 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7 -3
View File
@@ -4,13 +4,17 @@
CLAP (Contrastive Language-Audio Pretraining) is a model that learns acoustic concepts from natural language supervision and enables “Zero-Shot” inference. The model has been extensively evaluated in 26 audio downstream tasks achieving SoTA in several of them including classification, retrieval, and captioning. CLAP (Contrastive Language-Audio Pretraining) is a model that learns acoustic concepts from natural language supervision and enables “Zero-Shot” inference. The model has been extensively evaluated in 26 audio downstream tasks achieving SoTA in several of them including classification, retrieval, and captioning.
<img width="832" alt="clap_diagrams" src="./docs/diagram.png"> <img width="832" alt="clap_diagrams" src="https://raw.githubusercontent.com/hykilpikonna/CLAP/main/docs/diagram.png">
## Setup ## Setup
First, install python 3.8 or higher (3.11 recommended). Then, install CLAP: First, install python 3.8 or higher (3.11 recommended). Then, install CLAP using either of the following:
```shell ```shell
# Install pypi pacakge
pip install msclap
# Or Install latest (unstable) git source
pip install git+https://github.com/microsoft/CLAP.git pip install git+https://github.com/microsoft/CLAP.git
``` ```
@@ -52,7 +56,7 @@ captions = clap_model.generate_caption(file_paths: List[str])
``` ```
## Examples ## Examples
Take a look at `CLAP\src\` for usage examples. Take a look at [examples](./examples/) for usage examples.
To run Zero-Shot Classification on the ESC50 dataset try the following: To run Zero-Shot Classification on the ESC50 dataset try the following:
pyproject.toml
+1 -1
View File
@@ -1,6 +1,6 @@
[tool.poetry] [tool.poetry]
name = "msclap" name = "msclap"
version = "1.3.0" version = "1.3.1"
description = "CLAP (Contrastive Language-Audio Pretraining) is a model that learns acoustic concepts from natural language supervision and enables “Zero-Shot” inference. The model has been extensively evaluated in 26 audio downstream tasks achieving SoTA in several of them including classification, retrieval, and captioning." description = "CLAP (Contrastive Language-Audio Pretraining) is a model that learns acoustic concepts from natural language supervision and enables “Zero-Shot” inference. The model has been extensively evaluated in 26 audio downstream tasks achieving SoTA in several of them including classification, retrieval, and captioning."
authors = ["Benjamin Elizalde and Soham Deshmukh and Huaming Wang"] authors = ["Benjamin Elizalde and Soham Deshmukh and Huaming Wang"]
license = "MIT" license = "MIT"