update model card README.md

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_11_0
+metrics:
+- wer
+model-index:
+- name: whisper-tiny-be-test
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_11_0
+      type: common_voice_11_0
+      config: be
+      split: validation
+      args: be
+    metrics:
+    - name: Wer
+      type: wer
+      value: 75.27472527472527
+---
+
+<!-- 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-tiny-be-test
+
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_11_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9745
+- Wer: 75.2747
+
+## 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: 0.0001
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 5
+- training_steps: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 2.4473        | 0.5   | 10   | 1.3675          | 95.4212 |
+| 1.256         | 1.0   | 20   | 0.9745          | 75.2747 |
+
+
+### Framework versions
+
+- Transformers 4.26.0.dev0
+- Pytorch 1.13.0+cu116
+- Datasets 2.7.1.dev0
+- Tokenizers 0.13.2

train.log

@@ -1,3 +1,4 @@
 {'loss': 2.4473, 'learning_rate': 8.666666666666667e-05, 'epoch': 0.5}
 {'eval_loss': 1.3674653768539429, 'eval_wer': 95.42124542124543, 'eval_runtime': 44.1027, 'eval_samples_per_second': 1.451, 'eval_steps_per_second': 0.045, 'epoch': 0.5}
 {'loss': 1.256, 'learning_rate': 2e-05, 'epoch': 1.0}
+{'train_runtime': 33.8193, 'train_samples_per_second': 18.924, 'train_steps_per_second': 0.591, 'train_loss': 0.041942973931630455, 'epoch': 1.05}