update model card README.md

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_11_0
+metrics:
+- wer
+model-index:
+- name: openai/whisper-large-v2
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_11_0
+      type: common_voice_11_0
+      config: cs
+      split: test
+      args: cs
+    metrics:
+    - name: Wer
+      type: wer
+      value: 9.044032338262648
+---
+
+<!-- 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. -->
+
+# openai/whisper-large-v2
+
+This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_11_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2131
+- Wer: 9.0440
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 5000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.0149        | 4.25  | 1000 | 0.1622          | 10.0403 |
+| 0.0027        | 8.51  | 2000 | 0.1848          | 9.5136  |
+| 0.0008        | 12.76 | 3000 | 0.1930          | 9.3166  |
+| 0.0004        | 17.02 | 4000 | 0.2062          | 9.0330  |
+| 0.0003        | 21.28 | 5000 | 0.2131          | 9.0440  |
+
+
+### Framework versions
+
+- Transformers 4.26.0.dev0
+- Pytorch 1.13.0+cu117
+- Datasets 2.7.1
+- Tokenizers 0.13.2

run.log

@@ -436,3 +436,12 @@ xpu_backend=None,
 {'loss': 0.0003, 'learning_rate': 1.2222222222222225e-07, 'epoch': 21.06}
 {'loss': 0.0003, 'learning_rate': 6.666666666666668e-08, 'epoch': 21.17}
 {'loss': 0.0003, 'learning_rate': 1.1111111111111112e-08, 'epoch': 21.28}
+{'eval_loss': 0.2131042629480362, 'eval_wer': 9.044032338262648, 'eval_runtime': 12843.4698, 'eval_samples_per_second': 0.601, 'eval_steps_per_second': 0.075, 'epoch': 21.28}
+{'train_runtime': 245218.2405, 'train_samples_per_second': 1.305, 'train_steps_per_second': 0.02, 'train_loss': 0.02271956424098462, 'epoch': 21.28}
+12/16/2022 12:16:11 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
+12/16/2022 12:16:11 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
+12/16/2022 12:16:25 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow...        
+remote: LFS file scan complete.        
+To https://huggingface.co/mikr/whisper-large2-czech-cv11
+   07013c1..f0ad068  main -> main
+