Add fine-tuned Whisper Medium Sanskrit model

config.json

@@ -8,20 +8,33 @@
   "attention_dropout": 0.0,
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
-  "d_model": 1280,
-  "decoder_attention_heads": 20,
-  "decoder_ffn_dim": 5120,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 32,
+  "decoder_layers": 24,
   "decoder_start_token_id": 50258,
   "dropout": 0.0,
-  "dtype": "bfloat16",
-  "encoder_attention_heads": 20,
-  "encoder_ffn_dim": 5120,
+  "dtype": "float32",
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 32,
+  "encoder_layers": 24,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "mask_feature_length": 10,
@@ -34,13 +47,13 @@
   "max_target_positions": 448,
   "median_filter_width": 7,
   "model_type": "whisper",
-  "num_hidden_layers": 32,
+  "num_hidden_layers": 24,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
   "tie_word_embeddings": true,
-  "transformers_version": "5.3.0",
-  "use_cache": false,
+  "transformers_version": "5.2.0",
+  "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

generation_config.json

@@ -1,117 +1,47 @@
 {
   "alignment_heads": [
-    [
-      10,
-      12
-    ],
     [
       13,
-      17
-    ],
-    [
-      16,
-      11
-    ],
-    [
-      16,
-      12
-    ],
-    [
-      16,
-      13
-    ],
-    [
-      17,
       15
     ],
     [
-      17,
-      16
-    ],
-    [
-      18,
+      15,
       4
     ],
     [
-      18,
-      11
-    ],
-    [
-      18,
-      19
-    ],
-    [
-      19,
-      11
-    ],
-    [
-      21,
-      2
-    ],
-    [
-      21,
-      3
-    ],
-    [
-      22,
-      3
-    ],
-    [
-      22,
-      9
-    ],
-    [
-      22,
-      12
-    ],
-    [
-      23,
-      5
-    ],
-    [
-      23,
-      7
-    ],
-    [
-      23,
-      13
-    ],
-    [
-      25,
-      5
+      15,
+      15
     ],
     [
-      26,
+      16,
       1
     ],
     [
-      26,
-      12
+      20,
+      0
     ],
     [
-      27,
-      15
+      23,
+      4
     ]
   ],
-  "assistant_confidence_threshold": 0.4,
-  "assistant_lookbehind": 10,
   "begin_suppress_tokens": [
     220,
     50257
   ],
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
-  "diversity_penalty": 0.0,
-  "do_sample": false,
-  "early_stopping": false,
-  "encoder_no_repeat_ngram_size": 0,
-  "encoder_repetition_penalty": 1.0,
-  "eos_token_id": [
-    50257
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
   ],
-  "epsilon_cutoff": 0.0,
-  "eta_cutoff": 0.0,
-  "forced_decoder_ids": null,
   "is_multilingual": true,
   "lang_to_id": {
     "<|af|>": 50327,
@@ -214,36 +144,105 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "language": "hindi",
-  "length_penalty": 1.0,
   "max_initial_timestamp_index": 50,
   "max_length": 448,
-  "min_length": 0,
-  "no_repeat_ngram_size": 0,
   "no_timestamps_token_id": 50363,
-  "num_assistant_tokens": 20,
-  "num_assistant_tokens_schedule": "constant",
-  "num_beam_groups": 1,
-  "num_beams": 1,
-  "num_return_sequences": 1,
-  "output_scores": false,
   "pad_token_id": 50257,
   "prev_sot_token_id": 50361,
-  "remove_invalid_values": false,
-  "repetition_penalty": 1.0,
-  "return_dict_in_generate": false,
   "return_timestamps": false,
-  "suppress_tokens": [],
-  "target_lookbehind": 10,
-  "task": "transcribe",
+  "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,
+    50358,
+    50359,
+    50360,
+    50361,
+    50362
+  ],
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358
   },
-  "temperature": 1.0,
-  "top_k": 50,
-  "top_p": 1.0,
-  "transformers_version": "5.3.0",
-  "typical_p": 1.0,
-  "use_cache": true
+  "transformers_version": "5.2.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa5b61f7df3b30ab84d1bcfcebda5a82edd35a1dcd5e965ffe42fcb08d63bc01
-size 3086761032
+oid sha256:62f73550fa6db24b0c6f6c5962bd0dae80fa644e93cde9cd9c3792971b47fd28
+size 3055544304