Initial commit with updated tokenizer and processor

config.json

@@ -44,7 +44,7 @@
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
-  "max_length": 448,
+  "max_length": null,
   "max_source_positions": 1500,
   "max_target_positions": 448,
   "median_filter_width": 7,

generation_config.json

@@ -150,6 +150,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
+  "language": "french",
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,