Document only the published precisions
Browse files
README.md
CHANGED
|
@@ -17,16 +17,10 @@ Speech enhancement at 16 kHz. This model was converted to MLX format from
|
|
| 17 |
|
| 18 |
## Files
|
| 19 |
|
| 20 |
-
| file | size |
|
| 21 |
-
| --- | ---: |
|
| 22 |
-
| `model_fp32.safetensors` | 56 MB |
|
| 23 |
-
| `FRCRN_SE_16K.yaml` | 614 B |
|
| 24 |
-
| `weights.npz` | 110 MB | superseded |
|
| 25 |
-
|
| 26 |
-
fp32 only; no half-precision or quantized conversion is published.
|
| 27 |
-
|
| 28 |
-
`weights.npz` predates the safetensors conversion and is kept so that anything
|
| 29 |
-
already referring to it keeps working. Load `model_fp32.safetensors`.
|
| 30 |
|
| 31 |
## Used by
|
| 32 |
|
|
|
|
| 17 |
|
| 18 |
## Files
|
| 19 |
|
| 20 |
+
| file | size |
|
| 21 |
+
| --- | ---: |
|
| 22 |
+
| `model_fp32.safetensors` | 56 MB |
|
| 23 |
+
| `FRCRN_SE_16K.yaml` | 614 B |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
## Used by
|
| 26 |
|