End of training

README.md

@@ -16,6 +16,15 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper-tiny-en-us-minds14
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.3247
+- eval_wer_ortho: 36.7057
+- eval_wer: 36.6588
+- eval_runtime: 20.5021
+- eval_samples_per_second: 5.512
+- eval_steps_per_second: 0.39
+- epoch: 107.14
+- step: 3000
 
 ## Model description
 
@@ -41,7 +50,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- training_steps: 4000
 
 ### Framework versions
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "openai/whisper-tiny.en",
+  "_name_or_path": "openai/whisper-tiny",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -9,7 +9,7 @@
   "attention_dropout": 0.0,
   "begin_suppress_tokens": [
     220,
-    50256
+    50257
   ],
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
@@ -18,17 +18,25 @@
   "decoder_ffn_dim": 1536,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 4,
-  "decoder_start_token_id": 50257,
+  "decoder_start_token_id": 50258,
   "dropout": 0.0,
   "encoder_attention_heads": 6,
   "encoder_ffn_dim": 1536,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 4,
-  "eos_token_id": 50256,
+  "eos_token_id": 50257,
   "forced_decoder_ids": [
     [
       1,
-      50362
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
     ]
   ],
   "init_std": 0.02,
@@ -46,7 +54,7 @@
   "model_type": "whisper",
   "num_hidden_layers": 4,
   "num_mel_bins": 80,
-  "pad_token_id": 50256,
+  "pad_token_id": 50257,
   "scale_embedding": false,
   "suppress_tokens": [
     1,
@@ -72,77 +80,75 @@
     91,
     92,
     93,
-    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,
+    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
+    50361,
+    50362
   ],
   "torch_dtype": "float32",
   "transformers_version": "4.35.1",
   "use_cache": false,
   "use_weighted_layer_sum": false,
-  "vocab_size": 51864
+  "vocab_size": 51865
 }

generation_config.json

@@ -1,25 +1,13 @@
 {
   "alignment_heads": [
-    [
-      1,
-      0
-    ],
-    [
-      2,
-      0
-    ],
     [
       2,
-      5
+      2
     ],
     [
       3,
       0
     ],
-    [
-      3,
-      1
-    ],
     [
       3,
       2
@@ -31,26 +19,140 @@
     [
       3,
       4
+    ],
+    [
+      3,
+      5
     ]
   ],
   "begin_suppress_tokens": [
     220,
-    50256
+    50257
   ],
   "bos_token_id": 50257,
-  "decoder_start_token_id": 50257,
-  "eos_token_id": 50256,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
   "forced_decoder_ids": [
     [
       1,
-      50362
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
     ]
   ],
-  "is_multilingual": false,
+  "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
+  },
+  "language": "english",
   "max_initial_timestamp_index": 1,
   "max_length": 448,
-  "no_timestamps_token_id": 50362,
-  "pad_token_id": 50256,
+  "no_timestamps_token_id": 50363,
+  "pad_token_id": 50257,
   "return_timestamps": false,
   "suppress_tokens": [
     1,
@@ -76,73 +178,76 @@
     91,
     92,
     93,
-    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,
+    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
+    50361,
+    50362
   ],
+  "task": "transcribe",
+  "task_to_id": {
+    "transcribe": 50359,
+    "translate": 50358
+  },
   "transformers_version": "4.35.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:831f62443de237150ec851f27a0192427a8bab634857d9cd2b454d9db7b35541
-size 151060136
+oid sha256:027b3d66f24afd94d50350ebcaf9a989ceb6fd48ec52f95284c4c7fa87e79eb3
+size 151061672

runs/Nov22_22-06-34_L67DDV9G7R/events.out.tfevents.1700719599.L67DDV9G7R.91939.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d777a4dbca6586fcdcbff18e1cf52dda3a67437f74d1572e6be7ee5622edc8f
+size 29293

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfeb795886834490b18828520c7d8f0b81dd70b83ca6caa73a161a47e7902531
+oid sha256:7568170c03c6d5eb0ce47f667fa952d9d0ccd6264480ee48c53a163c07951d58
 size 4728