Update decoding.py

Following the suggestions of @Jeronymous in openai#914 and openai#924, it solves the problem of endless loop.

Author: FernanOrtega

whisper/decoding.py

@@ -470,6 +470,13 @@ def apply(self, logits: Tensor, tokens: Tensor):
             if timestamps.numel() > 0:
                 # timestamps shouldn't decrease; forbid timestamp tokens smaller than the last
                 logits[k, self.tokenizer.timestamp_begin : timestamps[-1]] = -np.inf
+                
+                # to force that timestamps are strictly increasing
+                if last_was_timestamp and not penultimate_was_timestamp:
+                    timestamp_last = timestamps[-1]
+                else:
+                    timestamp_last = timestamps[-1] + 1
+                logits[k, self.tokenizer.timestamp_begin: timestamp_last] = -np.inf
 
         if tokens.shape[1] == self.sample_begin:
             # suppress generating non-timestamp tokens at the beginning