End of training

README.md

@@ -0,0 +1,94 @@
+---
+library_name: peft
+language:
+- zh
+license: mit
+base_model: openai/whisper-large-v3-turbo
+tags:
+- wft
+- whisper
+- automatic-speech-recognition
+- audio
+- speech
+- generated_from_trainer
+datasets:
+- JacobLinCool/common_voice_16_1_zh_TW_clean_preprocessed
+metrics:
+- wer
+model-index:
+- name: whisper-large-v3-turbo-zh-TW-clean-1
+  results:
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: JacobLinCool/common_voice_16_1_zh_TW_clean_preprocessed
+      type: JacobLinCool/common_voice_16_1_zh_TW_clean_preprocessed
+    metrics:
+    - type: wer
+      value: 40.07234726688103
+      name: Wer
+---
+
+<!-- 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-large-v3-turbo-zh-TW-clean-1
+
+This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the JacobLinCool/common_voice_16_1_zh_TW_clean_preprocessed dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2641
+- Wer: 40.0723
+- Cer: 11.4336
+
+## 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: 0.0005
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     | Cer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|
+| No log        | 0      | 0    | 2.8297          | 83.7420 | 22.9952 |
+| 2.0577        | 0.9987 | 377  | 0.2666          | 47.9904 | 14.2907 |
+| 1.9482        | 2.0    | 755  | 0.2770          | 47.9703 | 14.4991 |
+| 1.1107        | 2.9987 | 1132 | 0.2886          | 48.4124 | 15.0615 |
+| 0.7225        | 4.0    | 1510 | 0.2736          | 46.2420 | 13.4020 |
+| 0.5901        | 4.9987 | 1887 | 0.2759          | 45.2572 | 13.7309 |
+| 0.4879        | 6.0    | 2265 | 0.2740          | 44.9759 | 12.9777 |
+| 0.1874        | 6.9987 | 2642 | 0.2663          | 44.2524 | 12.7316 |
+| 0.0544        | 8.0    | 3020 | 0.2712          | 42.6648 | 12.2295 |
+| 0.0128        | 8.9987 | 3397 | 0.2669          | 40.8963 | 11.6068 |
+| 0.004         | 9.9868 | 3770 | 0.2641          | 40.0723 | 11.4336 |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.4.0
+- Datasets 3.0.2
+- Tokenizers 0.20.1

runs/Oct28_19-44-58_66b66b87f409/events.out.tfevents.1730144707.66b66b87f409.2630.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4557ce681173cf0ade20281683520af7f5dc045f32086951e780c88795f1d652
-size 3967407
+oid sha256:f6697b21c263e1b49b364a6060b6e920c73e7e13dade0929a2fe7056e4f66d7d
+size 4284012