update model card README.md

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_11_0
+metrics:
+- wer
+model-index:
+- name: openai/whisper-medium
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_11_0
+      type: common_voice_11_0
+      config: sl
+      split: test
+      args: sl
+    metrics:
+    - name: Wer
+      type: wer
+      value: 17.988338192419825
+---
+
+<!-- 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-medium
+
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the common_voice_11_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4512
+- Wer: 17.9883
+
+## 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: 64
+- eval_batch_size: 32
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 5000
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.003         | 26.32  | 1000 | 0.3665          | 19.0379 |
+| 0.0001        | 52.63  | 2000 | 0.4114          | 18.1778 |
+| 0.0001        | 78.95  | 3000 | 0.4331          | 17.9300 |
+| 0.0           | 105.26 | 4000 | 0.4458          | 18.0321 |
+| 0.0           | 131.58 | 5000 | 0.4512          | 17.9883 |
+
+
+### Framework versions
+
+- Transformers 4.26.0.dev0
+- Pytorch 1.13.0+cu117
+- Datasets 2.7.1.dev0
+- Tokenizers 0.13.2

run.log

@@ -6382,3 +6382,10 @@ Time to load utils op: 0.0003142356872558594 seconds
 [2022-12-20 03:46:28,248] [INFO] [engine.py:2900:_get_all_zero_checkpoint_state_dicts] successfully read 1 ZeRO state_dicts for rank 0
 [2022-12-20 03:46:28,935] [INFO] [engine.py:2840:_load_zero_checkpoint] loading 1 zero partition checkpoints for rank 0
 {'train_runtime': 33627.3667, 'train_samples_per_second': 9.516, 'train_steps_per_second': 0.149, 'train_loss': 0.007872294521331787, 'epoch': 131.58}
+12/20/2022 03:47:54 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
+12/20/2022 03:47:54 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
+12/20/2022 03:48:00 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow...        
+remote: LFS file scan complete.        
+To https://huggingface.co/mikr/whisper-medium-sl-cv11
+   ccb40c0..c72c9a2  main -> main
+