Clarify Audio-JEPA training differences from the ICME checkpoint
Browse files- README.md +2 -0
- export_manifest.json +1 -1
README.md
CHANGED
|
@@ -44,6 +44,8 @@ weight to the Speech, Music, and Environment category means.
|
|
| 44 |
|
| 45 |
Audio-JEPA scores were supplied by the author for [run `jp6l70l6`](https://wandb.ai/tuncay-ludovic/audio%20embeddings/runs/jp6l70l6). The remaining scores are reported in the [project README](https://github.com/LudovicTuncay/audio-embeddings/blob/bb88bf790b1dcf8251c6b38e7a4766534adf33d3/README.md). These are reported research results, not a new benchmark run of the Transformers exports.
|
| 46 |
|
|
|
|
|
|
|
| 47 |
## Model and training
|
| 48 |
|
| 49 |
| Property | Value |
|
|
|
|
| 44 |
|
| 45 |
Audio-JEPA scores were supplied by the author for [run `jp6l70l6`](https://wandb.ai/tuncay-ludovic/audio%20embeddings/runs/jp6l70l6). The remaining scores are reported in the [project README](https://github.com/LudovicTuncay/audio-embeddings/blob/bb88bf790b1dcf8251c6b38e7a4766534adf33d3/README.md). These are reported research results, not a new benchmark run of the Transformers exports.
|
| 46 |
|
| 47 |
+
The Audio-JEPA row refers to the newer **16 kHz, 200,000-step** run, not the original ICME model (**32 kHz, 100,000 steps**). The author reports better results for this newer checkpoint.
|
| 48 |
+
|
| 49 |
## Model and training
|
| 50 |
|
| 51 |
| Property | Value |
|
export_manifest.json
CHANGED
|
@@ -27,7 +27,7 @@
|
|
| 27 |
},
|
| 28 |
"files": {
|
| 29 |
"CODE_LICENSE": "8fe9e8b749cd4abedabcb3100df445db899e72192394d14cc2dbf24a40811af6",
|
| 30 |
-
"README.md": "
|
| 31 |
"adapters.py": "ca0f26826763c0e48b7508da732242bb83adfeb4814e389ed3fde93ad648c728",
|
| 32 |
"config.json": "93452b1dfb678bafd2737b29cc80586e1ccd8368ad0183ed3b88ffd8f12ed6f2",
|
| 33 |
"configuration_audio.py": "59f3a0b8db0df5af85e677ac33a4431595e9b2eff6d34c1e6a1778dd75a4568d",
|
|
|
|
| 27 |
},
|
| 28 |
"files": {
|
| 29 |
"CODE_LICENSE": "8fe9e8b749cd4abedabcb3100df445db899e72192394d14cc2dbf24a40811af6",
|
| 30 |
+
"README.md": "88bf3617735c8e091c96f2c62b40329b0444e5299538f9e68eadc4409ca10a45",
|
| 31 |
"adapters.py": "ca0f26826763c0e48b7508da732242bb83adfeb4814e389ed3fde93ad648c728",
|
| 32 |
"config.json": "93452b1dfb678bafd2737b29cc80586e1ccd8368ad0183ed3b88ffd8f12ed6f2",
|
| 33 |
"configuration_audio.py": "59f3a0b8db0df5af85e677ac33a4431595e9b2eff6d34c1e6a1778dd75a4568d",
|