Aynursusuz/whisper_distil_small

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: openai/whisper-small
+license: mit
+base_model: distil-whisper/distil-small.en
 tags:
 - generated_from_trainer
 metrics:
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # music_speech_classification
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
+This model is a fine-tuned version of [distil-whisper/distil-small.en](https://huggingface.co/distil-whisper/distil-small.en) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0001
 - Accuracy: 1.0

config.json

@@ -8,7 +8,7 @@
   "attention_dropout": 0.0,
   "begin_suppress_tokens": [
     220,
-    50257
+    50256
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
@@ -16,27 +16,19 @@
   "decoder_attention_heads": 12,
   "decoder_ffn_dim": 3072,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 12,
-  "decoder_start_token_id": 50258,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50257,
   "dropout": 0.0,
   "dtype": "float32",
   "encoder_attention_heads": 12,
   "encoder_ffn_dim": 3072,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
-  "eos_token_id": 50257,
+  "eos_token_id": 50256,
   "forced_decoder_ids": [
     [
       1,
-      50259
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
+      50362
     ]
   ],
   "id2label": {
@@ -62,7 +54,7 @@
   "model_type": "whisper",
   "num_hidden_layers": 12,
   "num_mel_bins": 80,
-  "pad_token_id": 50257,
+  "pad_token_id": 50256,
   "scale_embedding": false,
   "suppress_tokens": [
     1,
@@ -88,72 +80,76 @@
     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,
+    357,
+    366,
+    438,
+    532,
+    685,
+    705,
+    796,
+    930,
+    1058,
+    1220,
+    1267,
+    1279,
+    1303,
+    1343,
+    1377,
+    1391,
+    1635,
+    1782,
+    1875,
+    2162,
+    2361,
+    2488,
+    3467,
+    4008,
+    4211,
+    4600,
+    4808,
+    5299,
+    5855,
+    6329,
+    7203,
+    9609,
+    9959,
+    10563,
+    10786,
+    11420,
+    11709,
+    11907,
+    13163,
+    13697,
+    13700,
+    14808,
+    15306,
+    16410,
+    16791,
+    17992,
+    19203,
+    19510,
+    20724,
+    22305,
+    22935,
+    27007,
+    30109,
+    30420,
+    33409,
+    34949,
+    40283,
+    40493,
+    40549,
+    47282,
+    49146,
+    50257,
+    50357,
+    50358,
+    50359,
     50360,
-    50361,
-    50362
+    50361
   ],
   "transformers_version": "4.57.1",
   "use_cache": true,
   "use_weighted_layer_sum": false,
-  "vocab_size": 51865
+  "vocab_size": 51864
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b0d2a67a73feb2092e2bc664cac7c53c85adedac2cd0f26034600ce6981228a
+oid sha256:a8076c3b27de42b8b8cd7f3d1e90723cf2dd8fa290d5d18d0cbd247030de93b5
 size 353426360

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0439dae1f541c5307f86b0db456f19f0950bc56727b6122c498634dd99978743
+oid sha256:b20772db450282b477a97e4998d3ff8cde60cd2d7ebd2f5ca2e0cec85d0f52f4
 size 5969