Upload DiCoWForConditionalGeneration

generation.py

@@ -122,6 +122,9 @@ class DiCoWGenerationMixin(WhisperForConditionalGeneration):
         task = getattr(generation_config, "task", None)
         language = getattr(generation_config, "language", None)
 
+        if "enrollments" in kwargs:
+            self.enrollments = kwargs["enrollments"]
+
         forced_decoder_ids = generation_config.forced_decoder_ids if hasattr(generation_config, "forced_decoder_ids") else None
         if forced_decoder_ids is not None:
             if language is None and task is None and forced_decoder_ids[0][1] is None:
@@ -142,6 +145,7 @@ class DiCoWGenerationMixin(WhisperForConditionalGeneration):
             return forced_decoder_ids
 
         init_tokens = super()._retrieve_init_tokens(input_features, batch_size, generation_config, config, num_segment_frames, kwargs)
+        del self.enrollments
         return init_tokens
 
     def detect_language(
@@ -200,6 +204,9 @@ class DiCoWGenerationMixin(WhisperForConditionalGeneration):
         with torch.no_grad():
 
             """<DiCoW CODE>"""
+            if hasattr(self, "enrollments"):
+                inputs["enrollments"] = self.enrollments
+
             logits = self(**inputs, decoder_input_ids=decoder_input_ids, use_cache=False,
                           stno_mask=self.stno_mask[:, :, :num_segment_frames // 2]).logits[:, -1]
             """</DiCoW CODE>"""

generation_config.json

@@ -1,240 +1,12 @@
 {
-  "alignment_heads": [
-    [
-      2,
-      4
-    ],
-    [
-      2,
-      11
-    ],
-    [
-      3,
-      3
-    ],
-    [
-      3,
-      6
-    ],
-    [
-      3,
-      11
-    ],
-    [
-      3,
-      14
-    ]
+  "_from_model_config": true,
+  "begin_suppress_tokens": [
+    220,
+    50256
   ],
-  "begin_suppress_tokens": null,
   "bos_token_id": 50257,
-  "ctc_margin": 0,
-  "ctc_weight": 0,
   "decoder_start_token_id": 50258,
   "eos_token_id": 50257,
-  "is_multilingual": true,
-  "lang_to_id": {
-    "<|af|>": 50327,
-    "<|am|>": 50334,
-    "<|ar|>": 50272,
-    "<|as|>": 50350,
-    "<|az|>": 50304,
-    "<|ba|>": 50355,
-    "<|be|>": 50330,
-    "<|bg|>": 50292,
-    "<|bn|>": 50302,
-    "<|bo|>": 50347,
-    "<|br|>": 50309,
-    "<|bs|>": 50315,
-    "<|ca|>": 50270,
-    "<|cs|>": 50283,
-    "<|cy|>": 50297,
-    "<|da|>": 50285,
-    "<|de|>": 50261,
-    "<|el|>": 50281,
-    "<|en|>": 50259,
-    "<|es|>": 50262,
-    "<|et|>": 50307,
-    "<|eu|>": 50310,
-    "<|fa|>": 50300,
-    "<|fi|>": 50277,
-    "<|fo|>": 50338,
-    "<|fr|>": 50265,
-    "<|gl|>": 50319,
-    "<|gu|>": 50333,
-    "<|haw|>": 50352,
-    "<|ha|>": 50354,
-    "<|he|>": 50279,
-    "<|hi|>": 50276,
-    "<|hr|>": 50291,
-    "<|ht|>": 50339,
-    "<|hu|>": 50286,
-    "<|hy|>": 50312,
-    "<|id|>": 50275,
-    "<|is|>": 50311,
-    "<|it|>": 50274,
-    "<|ja|>": 50266,
-    "<|jw|>": 50356,
-    "<|ka|>": 50329,
-    "<|kk|>": 50316,
-    "<|km|>": 50323,
-    "<|kn|>": 50306,
-    "<|ko|>": 50264,
-    "<|la|>": 50294,
-    "<|lb|>": 50345,
-    "<|ln|>": 50353,
-    "<|lo|>": 50336,
-    "<|lt|>": 50293,
-    "<|lv|>": 50301,
-    "<|mg|>": 50349,
-    "<|mi|>": 50295,
-    "<|mk|>": 50308,
-    "<|ml|>": 50296,
-    "<|mn|>": 50314,
-    "<|mr|>": 50320,
-    "<|ms|>": 50282,
-    "<|mt|>": 50343,
-    "<|my|>": 50346,
-    "<|ne|>": 50313,
-    "<|nl|>": 50271,
-    "<|nn|>": 50342,
-    "<|no|>": 50288,
-    "<|oc|>": 50328,
-    "<|pa|>": 50321,
-    "<|pl|>": 50269,
-    "<|ps|>": 50340,
-    "<|pt|>": 50267,
-    "<|ro|>": 50284,
-    "<|ru|>": 50263,
-    "<|sa|>": 50344,
-    "<|sd|>": 50332,
-    "<|si|>": 50322,
-    "<|sk|>": 50298,
-    "<|sl|>": 50305,
-    "<|sn|>": 50324,
-    "<|so|>": 50326,
-    "<|sq|>": 50317,
-    "<|sr|>": 50303,
-    "<|su|>": 50357,
-    "<|sv|>": 50273,
-    "<|sw|>": 50318,
-    "<|ta|>": 50287,
-    "<|te|>": 50299,
-    "<|tg|>": 50331,
-    "<|th|>": 50289,
-    "<|tk|>": 50341,
-    "<|tl|>": 50348,
-    "<|tr|>": 50268,
-    "<|tt|>": 50351,
-    "<|uk|>": 50280,
-    "<|ur|>": 50290,
-    "<|uz|>": 50337,
-    "<|vi|>": 50278,
-    "<|yi|>": 50335,
-    "<|yo|>": 50325,
-    "<|yue|>": 50358,
-    "<|zh|>": 50260
-  },
-  "language": null,
-  "max_initial_timestamp_index": null,
-  "max_length": 448,
-  "no_timestamps_token_id": 50364,
   "pad_token_id": 50257,
-  "prev_sot_token_id": 50362,
-  "return_timestamps": true,
-  "suppress_tokens": [
-    1,
-    2,
-    7,
-    8,
-    9,
-    10,
-    14,
-    25,
-    26,
-    27,
-    28,
-    29,
-    31,
-    58,
-    59,
-    60,
-    61,
-    62,
-    63,
-    90,
-    91,
-    92,
-    93,
-    359,
-    503,
-    522,
-    542,
-    873,
-    893,
-    902,
-    918,
-    922,
-    931,
-    1350,
-    1853,
-    1982,
-    2460,
-    2627,
-    3246,
-    3253,
-    3268,
-    3536,
-    3846,
-    3961,
-    4183,
-    4667,
-    6585,
-    6647,
-    7273,
-    9061,
-    9383,
-    10428,
-    10929,
-    11938,
-    12033,
-    12331,
-    12562,
-    13793,
-    14157,
-    14635,
-    15265,
-    15618,
-    16553,
-    16604,
-    18362,
-    18956,
-    20075,
-    21675,
-    22520,
-    26130,
-    26161,
-    26435,
-    28279,
-    29464,
-    31650,
-    32302,
-    32470,
-    36865,
-    42863,
-    47425,
-    49870,
-    50254,
-    50258,
-    50359,
-    50360,
-    50361,
-    50362,
-    50363
-  ],
-  "task": "transcribe",
-  "task_to_id": {
-    "transcribe": 50360,
-    "translate": 50359
-  },
   "transformers_version": "4.55.0"
 }