Update README.md
Browse files
README.md
CHANGED
|
@@ -28,8 +28,6 @@ the encoder is based on nvidia's nano codec that encodes your audio to 22khz FSQ
|
|
| 28 |
|
| 29 |
fill in the path to your data in [dune_extraction.py](https://huggingface.co/Respair/dune_codec/blob/main/dune_extraction.py), then run it. <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.
|
| 32 |
-
|
| 33 |
# important note
|
| 34 |
|
| 35 |
this is strictly a speech tokenizer, trained only on human speech; it won't do well with music.
|
|
|
|
| 28 |
|
| 29 |
fill in the path to your data in [dune_extraction.py](https://huggingface.co/Respair/dune_codec/blob/main/dune_extraction.py), then run it. <br><br>
|
| 30 |
|
|
|
|
|
|
|
| 31 |
# important note
|
| 32 |
|
| 33 |
this is strictly a speech tokenizer, trained only on human speech; it won't do well with music.
|