Create README.md

README.md

@@ -0,0 +1,86 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- afrispeech-200
+metrics:
+- wer
+model-index:
+- name: afrispeech_large_h100_no_puncs_last
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: afrispeech-200
+      type: afrispeech-200
+      config: all
+      split: train
+      args: all
+    metrics:
+    - name: Wer
+      type: wer
+      value: 6.152856683460177
+---
+
+<!-- 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. -->
+
+# afrispeech_large_h100_no_puncs_last
+
+This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the afrispeech-200 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1213
+- Wer: 6.1529
+
+## 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: 32
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- 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: 2000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.1578        | 0.1   | 200  | 0.1283          | 5.8313 |
+| 0.1253        | 0.2   | 400  | 0.1475          | 6.8282 |
+| 0.236         | 0.3   | 600  | 0.1505          | 7.2033 |
+| 0.1628        | 0.4   | 800  | 0.1398          | 8.2217 |
+| 0.1213        | 1.05  | 1000 | 0.1316          | 6.1743 |
+| 0.0569        | 1.15  | 1200 | 0.1417          | 6.7960 |
+| 0.0598        | 1.25  | 1400 | 0.1445          | 7.0104 |
+| 0.1262        | 1.35  | 1600 | 0.1269          | 6.4101 |
+| 0.0462        | 2.0   | 1800 | 0.1186          | 5.9706 |
+| 0.0487        | 2.1   | 2000 | 0.1213          | 6.1529 |
+
+
+### Framework versions
+
+- Transformers 4.29.1
+- Pytorch 1.13.1
+- Datasets 2.12.0
+- Tokenizers 0.13.3