update model card README.md

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_11_0
+metrics:
+- wer
+model-index:
+- name: whisper-base-belarusian
+  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: 12.206885082321635
+---
+
+<!-- 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-base-belarusian
+
+This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice_11_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1080
+- Wer: 12.2069
+
+## 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: 64
+- 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: 500
+- training_steps: 6000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.2445        | 0.17  | 1000 | 0.3059          | 32.4163 |
+| 0.1823        | 0.33  | 2000 | 0.2004          | 22.1259 |
+| 0.1412        | 0.5   | 3000 | 0.1752          | 20.0700 |
+| 0.1093        | 0.67  | 4000 | 0.1413          | 16.0533 |
+| 0.1137        | 0.83  | 5000 | 0.1155          | 13.3108 |
+| 0.0585        | 1.1   | 6000 | 0.1080          | 12.2069 |
+
+
+### Framework versions
+
+- Transformers 4.26.0.dev0
+- Pytorch 1.13.0+cu117
+- Datasets 2.7.1.dev0
+- Tokenizers 0.13.2

train_20221217-004912.log

@@ -131,3 +131,10 @@ xpu_backend=None,
 12/17/2022 02:39:16 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [1/20]
 12/17/2022 03:40:45 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['src/__pycache__/preprocess.cpython-38.pyc', 'src/__pycache__/run_speech_recognition_seq2seq_streaming.cpython-38.pyc']. This may take a bit of time if the files are large.
 12/17/2022 16:02:39 - INFO - __main__ - ShuffleCallback. shuffling train dataset. seed: 42. dataset epoch: 1
+12/17/2022 17:58:40 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
+12/17/2022 17:58:40 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
+12/17/2022 17:58:44 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow...        
+remote: LFS file scan complete.        
+To https://huggingface.co/ales/whisper-base-belarusian
+   4074dad..52d55ef  main -> main
+

train_run_1.log

@@ -36372,3 +36372,20 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|tokenization_utils_base.py:2157] 2022-12-17 17:58:19,260 >> tokenizer config file saved in ./tokenizer_config.json
 [INFO|tokenization_utils_base.py:2164] 2022-12-17 17:58:19,260 >> Special tokens file saved in ./special_tokens_map.json
 [INFO|tokenization_utils_base.py:2210] 2022-12-17 17:58:19,260 >> added tokens file saved in ./added_tokens.json
+Several commits (2) will be pushed upstream.
+{'eval_loss': 0.10796044021844864, 'eval_wer': 12.206885082321635, 'eval_runtime': 2137.698, 'eval_samples_per_second': 7.425, 'eval_steps_per_second': 0.232, 'epoch': 1.1}
+{'train_runtime': 61737.3829, 'train_samples_per_second': 6.22, 'train_steps_per_second': 0.097, 'train_loss': 0.17721048017342886, 'epoch': 1.1}
+12/17/2022 17:58:40 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
+The progress bars may be unreliable.
+12/17/2022 17:58:40 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
+
+remote: LFS file scan complete.        
+To https://huggingface.co/ales/whisper-base-belarusian
+   4074dad..52d55ef  main -> main
+
+12/17/2022 17:58:44 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow...        
+remote: LFS file scan complete.        
+To https://huggingface.co/ales/whisper-base-belarusian
+   4074dad..52d55ef  main -> main
+
+