update SISNR doc to make it clear we display minus the SISNR (#268)

* doc

* making doc clearer

* line too long

audiocraft/losses/sisnr.py

@@ -41,6 +41,11 @@ class SISNR(nn.Module):
 
     Input should be [B, C, T], output is scalar.
 
+    ..Warning:: This function returns the opposite of the SI-SNR (e.g. `-1 * regular_SI_SNR`).
+        Consequently, lower scores are better in terms of reconstruction quality,
+        in particular, it should be negative if training goes well. This done this way so
+        that this module can also be used as a loss function for training model.
+
     Args:
         sample_rate (int): Sample rate.
         segment (float or None): Evaluate on chunks of that many seconds. If None, evaluate on

docs/METRICS.md

@@ -16,6 +16,10 @@ We provide an implementation of the Scale-Invariant Signal-to-Noise Ratio in PyT
 No specific requirement is needed for this metric. Please activate the metric at the
 evaluation stage with the appropriate flag:
 
+**Warning:** We report the opposite of the SI-SNR, e.g. multiplied by -1. This is due to internal 
+    details where the SI-SNR score can also be used as a training loss function, where lower
+    values should indicate better reconstruction. Negative values are such expected and a good sign! Those should be again multiplied by `-1` before publication :)
+
 ```shell
 dora run <...> evaluate.metrics.sisnr=true
 ```