End of training

README.md

@@ -2,10 +2,12 @@
 language:
 - en
 license: apache-2.0
-base_model: openai/whisper-base
+base_model: openai/whisper-base.en
 tags:
 - hf-asr-leaderboard
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: Whisper Base EN
   results: []
@@ -16,7 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Base EN
 
-This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Common Voice 11.0 dataset.
+This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on the ADLINK dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0003
+- Wer: 1.2422
 
 ## Model description
 
@@ -36,14 +41,30 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
 - training_steps: 1000
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 1.4205        | 33.33  | 100  | 1.0960          | 9.9379 |
+| 0.4057        | 66.67  | 200  | 0.3715          | 1.5528 |
+| 0.0908        | 100.0  | 300  | 0.0704          | 1.5528 |
+| 0.0053        | 133.33 | 400  | 0.0037          | 1.5528 |
+| 0.0011        | 166.67 | 500  | 0.0010          | 1.2422 |
+| 0.0006        | 200.0  | 600  | 0.0006          | 1.2422 |
+| 0.0004        | 233.33 | 700  | 0.0004          | 1.2422 |
+| 0.0003        | 266.67 | 800  | 0.0003          | 1.2422 |
+| 0.0003        | 300.0  | 900  | 0.0003          | 1.2422 |
+| 0.0003        | 333.33 | 1000 | 0.0003          | 1.2422 |
+
+
 ### Framework versions
 
 - Transformers 4.38.0.dev0

generation_config.json

@@ -2,14 +2,6 @@
   "alignment_heads": [
     [
       3,
-      1
-    ],
-    [
-      4,
-      2
-    ],
-    [
-      4,
       3
     ],
     [
@@ -22,141 +14,32 @@
     ],
     [
       5,
-      2
+      5
     ],
     [
       5,
-      4
-    ],
-    [
-      5,
-      6
+      7
     ]
   ],
   "begin_suppress_tokens": [
     220,
-    50257
+    50256
   ],
   "bos_token_id": 50257,
-  "decoder_start_token_id": 50258,
-  "eos_token_id": 50257,
+  "decoder_start_token_id": 50257,
+  "eos_token_id": 50256,
   "forced_decoder_ids": [
     [
       1,
-      null
-    ],
-    [
-      2,
-      50359
+      50362
     ]
   ],
-  "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,
-    "<|zh|>": 50260
-  },
+  "is_multilingual": false,
   "max_initial_timestamp_index": 50,
   "max_length": 448,
-  "no_timestamps_token_id": 50363,
-  "pad_token_id": 50257,
-  "prev_sot_token_id": 50361,
+  "no_timestamps_token_id": 50362,
+  "pad_token_id": 50256,
+  "prev_sot_token_id": 50360,
   "return_timestamps": false,
   "suppress_tokens": [
     1,
@@ -182,75 +65,73 @@
     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
   ],
-  "task_to_id": {
-    "transcribe": 50359,
-    "translate": 50358
-  },
   "transformers_version": "4.38.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2f87d009fcfc213b5e53a3eca817bc6349e0304eebfe943947df3945ee9808
+oid sha256:fe91f57490bd471d39f4532ce01f7a25d8440a23a111ab2a08d0ff87dd4d440b
 size 290401888