Update README.md
Browse files
README.md
CHANGED
|
@@ -26,4 +26,6 @@ the encoder is based on nvidia's nano codec that encodes your audio to 22khz FSQ
|
|
| 26 |
|
| 27 |
# Extract / Inference
|
| 28 |
|
| 29 |
-
visit [dune_extraction.py](
|
|
|
|
|
|
|
|
|
| 26 |
|
| 27 |
# Extract / Inference
|
| 28 |
|
| 29 |
+
visit [dune_extraction.py](https://huggingface.co/Respair/dune_codec/blob/main/dune_extraction.py) <br><br>
|
| 30 |
+
|
| 31 |
+
you need a dataset with audio embedded and a `key` column. if your metadata and audio are in one place, you can just DATASET_SOURCE == AUDIO_DATASET_SOURCE.
|