End of training

README.md

@@ -0,0 +1,92 @@
+---
+library_name: transformers
+language:
+- hr
+license: apache-2.0
+base_model: openai/whisper-large-v3
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: whisper-large-v3-turbo-hr-parla
+  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-turbo-hr-parla
+
+This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the classla/ParlaSpeech-HR dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0816
+- Wer: 0.0352
+
+## 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: 6.25e-06
+- train_batch_size: 64
+- eval_batch_size: 32
+- seed: 42
+- 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: 800
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Wer    |
+|:-------------:|:------:|:-----:|:---------------:|:------:|
+| 0.1485        | 0.0703 | 1000  | 0.1376          | 0.0610 |
+| 0.1399        | 0.1406 | 2000  | 0.1210          | 0.0545 |
+| 0.1311        | 0.2108 | 3000  | 0.1144          | 0.0529 |
+| 0.119         | 0.2811 | 4000  | 0.1058          | 0.0487 |
+| 0.1165        | 0.3514 | 5000  | 0.1067          | 0.0517 |
+| 0.1142        | 0.4217 | 6000  | 0.1007          | 0.0464 |
+| 0.1095        | 0.4920 | 7000  | 0.1019          | 0.0447 |
+| 0.1112        | 0.5622 | 8000  | 0.0974          | 0.0425 |
+| 0.1104        | 0.6325 | 9000  | 0.0971          | 0.0442 |
+| 0.1081        | 0.7028 | 10000 | 0.0943          | 0.0411 |
+| 0.1025        | 0.7731 | 11000 | 0.0905          | 0.0397 |
+| 0.1042        | 0.8433 | 12000 | 0.0930          | 0.0419 |
+| 0.1031        | 0.9136 | 13000 | 0.0923          | 0.0428 |
+| 0.1038        | 0.9839 | 14000 | 0.0894          | 0.0408 |
+| 0.0878        | 1.0542 | 15000 | 0.0902          | 0.0408 |
+| 0.0886        | 1.1245 | 16000 | 0.0869          | 0.0369 |
+| 0.0864        | 1.1947 | 17000 | 0.0861          | 0.0364 |
+| 0.0817        | 1.2650 | 18000 | 0.0867          | 0.0408 |
+| 0.0899        | 1.3353 | 19000 | 0.0852          | 0.0383 |
+| 0.0868        | 1.4056 | 20000 | 0.0846          | 0.0369 |
+| 0.0858        | 1.4759 | 21000 | 0.0844          | 0.0378 |
+| 0.0827        | 1.5461 | 22000 | 0.0845          | 0.0391 |
+| 0.0798        | 1.6164 | 23000 | 0.0846          | 0.0378 |
+| 0.0845        | 1.6867 | 24000 | 0.0833          | 0.0375 |
+| 0.0768        | 1.7570 | 25000 | 0.0840          | 0.0375 |
+| 0.0799        | 1.8273 | 26000 | 0.0837          | 0.0375 |
+| 0.0808        | 1.8975 | 27000 | 0.0825          | 0.0352 |
+| 0.0837        | 1.9678 | 28000 | 0.0816          | 0.0352 |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

generation_config.json

@@ -0,0 +1,152 @@
+{
+  "alignment_heads": [
+    [
+      2,
+      4
+    ],
+    [
+      2,
+      11
+    ],
+    [
+      3,
+      3
+    ],
+    [
+      3,
+      6
+    ],
+    [
+      3,
+      11
+    ],
+    [
+      3,
+      14
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "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
+  },
+  "language": "croatian",
+  "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": "transcribe",
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c1ce8423da10e0ed25c08a8794b15482084bb2d4d9a45ea17ea98a0ddae2a9
+oid sha256:1fc519ad72278d625746a651939e43db3e98b54ef10a8370cec71461b1f0206c
 size 3235581408

runs/Dec28_08-27-33_stablediffusion/events.out.tfevents.1735374503.stablediffusion.2273.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b36556363ac099ea3e307f60ead879ead261b4239a212a1ae0b2f50f44103db
-size 77106
+oid sha256:c5add493412658cd306b73c1483a6f3d7f1b2024633d11a38ce2d2cdd4a390a9
+size 77466