End of training

README.md

@@ -7,25 +7,35 @@ tags:
 - generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_17_0
+metrics:
+- wer
 model-index:
-- name: Whisper Large-v3 Hu - snoopyben27
-  results: []
+- name: Whisper Large-v3 Hu_v2 - snoopyben27
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice 17.0
+      type: mozilla-foundation/common_voice_17_0
+      config: default
+      split: test
+      args: 'config: hu, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 14.057158484889923
 ---
 
 <!-- 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 Hu - snoopyben27
+# Whisper Large-v3 Hu_v2 - snoopyben27
 
 This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the Common Voice 17.0 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.1072
-- eval_wer: 11.8966
-- eval_runtime: 966.6053
-- eval_samples_per_second: 1.035
-- eval_steps_per_second: 0.259
-- epoch: 0.6596
-- step: 1000
+- Loss: 0.1284
+- Wer: 14.0572
 
 ## Model description
 
@@ -45,15 +55,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 32
+- train_batch_size: 8
 - eval_batch_size: 4
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
-- training_steps: 2000
+- lr_scheduler_warmup_steps: 10
+- training_steps: 250
 - mixed_precision_training: Native AMP
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.1306        | 0.0825 | 250  | 0.1284          | 14.0572 |
+
+
 ### Framework versions
 
 - Transformers 4.41.2

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eb0dcdc38091ca5c0475407d19a365946dec4fb1aa5feab075e915c5189bfdd
+oid sha256:274d9b9115b2266d8d66129b8c4c93dc9fb9ea5ec72c3cd3cf134e8a519e5d75
 size 4993448880

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8edc4309db958f881dac40a859408618cb91ea43b68c05fbb84e4131b62ce53
+oid sha256:fbde048a6f500acc3c2a3240fb0cc29e9a8c0885850c6c2115174cedb9acfcd6
 size 1180663192

runs/Jun27_15-41-36_c86079fec55a/events.out.tfevents.1719502907.c86079fec55a.490.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51518977ce7d1f8e7e48af22417c7a0861b2313321547674d72b58c674314dae
-size 7998
+oid sha256:ae0ff62a284bdbc081cd6a7b87585456ea64e584438148947a9ed2e7093bfdca
+size 8352