End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: lasion/wav2vec2-base-timit-demo-google-colab
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: wav2vec2-base-timit-demo-google-colab
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # wav2vec2-base-timit-demo-google-colab
 
 This model is a fine-tuned version of [lasion/wav2vec2-base-timit-demo-google-colab](https://huggingface.co/lasion/wav2vec2-base-timit-demo-google-colab) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6814
+- Wer: 0.5670
 
 ## Model description
 
@@ -39,11 +44,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 1
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.6582        | 1.0   | 500  | 0.6814          | 0.5670 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be9f4ce8f373fccc670f71265da5b5bf30afc73e9a32bc3878e8ae9013a55749
+oid sha256:0edb916d9d3ae437b8c139ce935fa87dc4a3d0703f764557c5e8fe0e2b8903b5
 size 377611120

runs/Apr02_03-37-43_f96aab1f5bfb/events.out.tfevents.1712029158.f96aab1f5bfb.4310.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79d9131d564300ff1f25560c1b655d312c91ccf0b5fd294945503308496a5e7
+size 7284

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aec71c36b1c34914a5ab5b9a2f4c2fe3e2edbcad265279651e583574b184440c
+oid sha256:939c2e57b25db60a9b16a1f164dd9e070f393eadebd66028cdaadc695e5d4416
 size 4920