End of training

README.md

@@ -1,7 +1,9 @@
 ---
+library_name: transformers
 language:
 - en
 license: apache-2.0
+base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 model-index:
@@ -39,10 +41,10 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 2
 - total_train_batch_size: 16
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 20
-- num_epochs: 20
+- lr_scheduler_warmup_steps: 30
+- num_epochs: 40
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -51,6 +53,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.27.4
-- Pytorch 2.8.0+cu128
-- Tokenizers 0.13.3
+- Transformers 4.51.0
+- Pytorch 2.7.1+cu126
+- Datasets 4.1.1
+- Tokenizers 0.21.4

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "openai/whisper-small",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,
@@ -7,10 +6,7 @@
     "WhisperForConditionalGeneration"
   ],
   "attention_dropout": 0.0,
-  "begin_suppress_tokens": [
-    220,
-    50257
-  ],
+  "begin_suppress_tokens": null,
   "bos_token_id": 50257,
   "classifier_proj_size": 256,
   "d_model": 768,
@@ -47,104 +43,17 @@
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
   "mask_time_prob": 0.05,
-  "max_length": 448,
+  "max_length": null,
   "max_source_positions": 1500,
   "max_target_positions": 448,
+  "median_filter_width": 7,
   "model_type": "whisper",
   "num_hidden_layers": 12,
   "num_mel_bins": 80,
   "pad_token_id": 50257,
   "scale_embedding": false,
-  "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,
-    50360,
-    50361,
-    50362
-  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.51.0",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -241,8 +241,6 @@
     49870,
     50254,
     50258,
-    50358,
-    50359,
     50360,
     50361,
     50362
@@ -252,5 +250,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.27.4"
+  "transformers_version": "4.51.0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ee451da59695bd639854c2ec1e5f2e3d7081b3b0f5a7b02ff2cf72dd697e3b
+size 966995080

preprocessor_config.json

@@ -1,5 +1,6 @@
 {
   "chunk_length": 30,
+  "dither": 0.0,
   "feature_extractor_type": "WhisperFeatureExtractor",
   "feature_size": 80,
   "hop_length": 160,

runs/Sep27_22-35-46_alien/events.out.tfevents.1759026947.alien.160413.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2fc959802f541c22ffc9cc1263557a1ab5d204e470ab61732359fa447dfbf3
+size 7070

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4241e95fb02fc622a352535f4e9552ff1a036d59b2364d6cba139fea687825
-size 4561
+oid sha256:7594a8f94213ac7f5b7ba2093660c11ce70c222ea36f53c78d283d7f61d4e086
+size 5905