End of training

README.md

@@ -0,0 +1,94 @@
+---
+base_model: openai/whisper-large-v3
+datasets:
+- mozilla-foundation/common_voice_11_0
+language:
+- th
+library_name: peft
+license: apache-2.0
+metrics:
+- wer
+- bleu
+tags:
+- generated_from_trainer
+model-index:
+- name: Whisper Large V3 Thai Lora - Magi Boss
+  results:
+  - task:
+      type: automatic-speech-recognition
+      name: Automatic Speech Recognition
+    dataset:
+      name: Common Voice 11.0
+      type: mozilla-foundation/common_voice_11_0
+      config: th
+      split: None
+      args: 'config: th, split: validation'
+    metrics:
+    - type: wer
+      value: 0.8100890207715133
+      name: Wer
+    - type: bleu
+      value: 8.739138222980559
+      name: Bleu
+---
+
+<!-- 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 Thai Lora - Magi Boss
+
+This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 11.0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1894
+- Wer: 0.8101
+- Ter: {'score': 81.00890207715133, 'num_edits': 546, 'ref_length': 674.0}
+- Chrf: {'score': 87.48106146298329, 'char_order': 6, 'word_order': 0, 'beta': 2}
+- Cer: 0.1041
+- Bleu: 8.7391
+- Average Suber: 0.8189
+
+## 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: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 25
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    | Ter                                                                 | Chrf                                                                      | Cer    | Bleu   | Average Suber |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------------------------------------------------------------------:|:-------------------------------------------------------------------------:|:------:|:------:|:-------------:|
+| 0.3053        | 0.32  | 50   | 0.2052          | 0.8457 | {'score': 84.56973293768546, 'num_edits': 570, 'ref_length': 674.0} | {'score': 86.69717825036054, 'char_order': 6, 'word_order': 0, 'beta': 2} | 0.1115 | 7.8703 | 0.8640        |
+| 0.3752        | 0.64  | 100  | 0.1937          | 0.8323 | {'score': 83.23442136498517, 'num_edits': 561, 'ref_length': 674.0} | {'score': 86.98005540895491, 'char_order': 6, 'word_order': 0, 'beta': 2} | 0.1087 | 8.1510 | 0.8469        |
+| 0.2794        | 0.96  | 150  | 0.1894          | 0.8101 | {'score': 81.00890207715133, 'num_edits': 546, 'ref_length': 674.0} | {'score': 87.48106146298329, 'char_order': 6, 'word_order': 0, 'beta': 2} | 0.1041 | 8.7391 | 0.8189        |
+
+
+### Framework versions
+
+- PEFT 0.12.1.dev0
+- Transformers 4.45.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

runs/Aug06_21-16-30_0992a6553fa1/events.out.tfevents.1722978995.0992a6553fa1.1460.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae9bf081364df76307e209521c94767af894114c358ab9be7b3a3616058c570
-size 38820
+oid sha256:ca63f4408854e960bb0bcecb3c0c7e1ee89b328b73e6257b4563d437f7669e7c
+size 40440