Merge pull request #148 from FernanOrtega/main

Update decoding.py

whisperx/decoding.py

@@ -413,7 +413,8 @@ def apply(self, logits: Tensor, tokens: Tensor):
 
         # timestamps have to appear in pairs, except directly before EOT; mask logits accordingly
         for k in range(tokens.shape[0]):
-            seq = [t for t in tokens[k, self.sample_begin :].tolist()]
+            sampled_tokens = tokens[k, self.sample_begin :]
+            seq = [t for t in sampled_tokens.tolist()]
             last_was_timestamp = len(seq) >= 1 and seq[-1] >= self.tokenizer.timestamp_begin
             penultimate_was_timestamp = len(seq) < 2 or seq[-2] >= self.tokenizer.timestamp_begin
 
@@ -422,6 +423,11 @@ def apply(self, logits: Tensor, tokens: Tensor):
                     logits[k, self.tokenizer.timestamp_begin :] = -np.inf
                 else:  # cannot be normal text tokens
                     logits[k, : self.tokenizer.eot] = -np.inf
+
+            timestamps = sampled_tokens[sampled_tokens.ge(self.tokenizer.timestamp_begin)]
+            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
 
         if tokens.shape[1] == self.sample_begin:
             # suppress generating non-timestamp tokens at the beginning