End of training

README.md

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: openai/whisper-large-v3
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: whisper-large-v3-genbed-m-model
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# whisper-large-v3-genbed-m-model
+
+This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7479
+- Wer: 36.9425
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1.75e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 30000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Wer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 1.4385        | 0.6596  | 250  | 0.7026          | 57.3435 |
+| 0.578         | 1.3193  | 500  | 0.6312          | 47.4271 |
+| 0.499         | 1.9789  | 750  | 0.5735          | 43.2676 |
+| 0.2829        | 2.6385  | 1000 | 0.5949          | 41.0913 |
+| 0.2304        | 3.2982  | 1250 | 0.6149          | 40.5660 |
+| 0.1672        | 3.9578  | 1500 | 0.5645          | 38.5399 |
+| 0.1019        | 4.6174  | 1750 | 0.6265          | 42.0026 |
+| 0.0911        | 5.2770  | 2000 | 0.6534          | 38.5399 |
+| 0.0713        | 5.9367  | 2250 | 0.6533          | 38.1754 |
+| 0.0545        | 6.5963  | 2500 | 0.6577          | 37.7466 |
+| 0.0497        | 7.2559  | 2750 | 0.6626          | 39.3117 |
+| 0.0425        | 7.9156  | 3000 | 0.6901          | 37.2642 |
+| 0.0374        | 8.5752  | 3250 | 0.6919          | 38.6256 |
+| 0.0312        | 9.2348  | 3500 | 0.7093          | 37.2856 |
+| 0.0302        | 9.8945  | 3750 | 0.7260          | 35.7740 |
+| 0.0233        | 10.5541 | 4000 | 0.7181          | 36.5780 |
+| 0.0262        | 11.2137 | 4250 | 0.7352          | 35.5703 |
+| 0.0241        | 11.8734 | 4500 | 0.7340          | 36.4172 |
+| 0.0198        | 12.5330 | 4750 | 0.7463          | 36.8461 |
+| 0.0201        | 13.1926 | 5000 | 0.7479          | 36.9425 |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,177 @@
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50360
+    ]
+  ],
+  "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,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50364,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50362,
+  "return_timestamps": false,
+  "suppress_tokens": [],
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": false
+}

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fabc300caed6691b10feab4ea5d548d34913aba094f20bbd07a29128f8994a4d
+oid sha256:c39fcd88ade1ee0056f1b1a51a2642dc1908af5102e236a189121b24aae8edd1
 size 4993448880

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92644a474d0c4deb1cce7ac22ccab6b9890c394fc6083f0c153cc676a5ddeaa5
+oid sha256:2513f9192645fb819a03ebcfabf8474e32f6d33d7f291f829a7b933780ac8e17
 size 1180663192

runs/Sep22_10-14-44_3292f9031309/events.out.tfevents.1727000099.3292f9031309.7101.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b7718bc109d8431fe5bb5dc70cac5723e297b4a4245657d3e3c7aeaac6244d7
-size 16402
+oid sha256:6f10d28e596eacbfcc0bda8597055b9998aad1509b0433e9829ff5a5846a274c
+size 16756