holmes26/fluent-clean-wav2vec

README.md

@@ -1,10 +1,10 @@
 ---
 license: apache-2.0
+base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
 metrics:
 - wer
-base_model: facebook/wav2vec2-base
 model-index:
 - name: models
   results: []
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0108
-- Wer: 0.2638
+- Loss: 0.0095
+- Wer: 0.2644
 
 ## Model description
 
@@ -51,21 +51,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 4.7187        | 1.26  | 500  | 2.7805          | 1.0    |
-| 1.3764        | 2.53  | 1000 | 0.2018          | 0.4834 |
-| 0.2713        | 3.79  | 1500 | 0.0572          | 0.3337 |
-| 0.1924        | 5.05  | 2000 | 0.0486          | 0.3029 |
-| 0.1283        | 6.31  | 2500 | 0.0254          | 0.2865 |
-| 0.095         | 7.58  | 3000 | 0.0879          | 0.2924 |
-| 0.0885        | 8.84  | 3500 | 0.0168          | 0.2702 |
-| 0.0662        | 10.1  | 4000 | 0.0196          | 0.2708 |
-| 0.0646        | 11.36 | 4500 | 0.0125          | 0.2697 |
-| 0.0487        | 12.63 | 5000 | 0.0144          | 0.2691 |
-| 0.0539        | 13.89 | 5500 | 0.0172          | 0.2673 |
-| 0.0331        | 15.15 | 6000 | 0.0109          | 0.2656 |
-| 0.0354        | 16.41 | 6500 | 0.0125          | 0.2656 |
-| 0.0194        | 17.68 | 7000 | 0.0115          | 0.2650 |
-| 0.0156        | 18.94 | 7500 | 0.0108          | 0.2638 |
+| 4.7071        | 1.26  | 500  | 2.7976          | 0.9918 |
+| 1.4121        | 2.53  | 1000 | 0.1923          | 0.5114 |
+| 0.2774        | 3.79  | 1500 | 0.0824          | 0.3238 |
+| 0.1805        | 5.05  | 2000 | 0.0502          | 0.3058 |
+| 0.1232        | 6.31  | 2500 | 0.0336          | 0.2930 |
+| 0.0949        | 7.58  | 3000 | 0.0169          | 0.2685 |
+| 0.094         | 8.84  | 3500 | 0.0202          | 0.2772 |
+| 0.0779        | 10.1  | 4000 | 0.0203          | 0.2708 |
+| 0.0653        | 11.36 | 4500 | 0.0177          | 0.2702 |
+| 0.055         | 12.63 | 5000 | 0.0225          | 0.2667 |
+| 0.0481        | 13.89 | 5500 | 0.0135          | 0.2650 |
+| 0.0317        | 15.15 | 6000 | 0.0167          | 0.2656 |
+| 0.0339        | 16.41 | 6500 | 0.0126          | 0.2650 |
+| 0.0238        | 17.68 | 7000 | 0.0113          | 0.2650 |
+| 0.018         | 18.94 | 7500 | 0.0095          | 0.2644 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ee6cc0f466585b6072a8dcdb303490f9a1935b5f91690844677f49e8c9376b9
+oid sha256:4a39fd81a608248114fc3c8bf31b39d494761f3c8ee751df036b27f11ee440ff
 size 377611120

runs/Apr12_04-43-19_1a8fc3f508fd/events.out.tfevents.1712897177.1a8fc3f508fd.854.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc874ee02accfea76c628aaf0151b40ab68a1e0b230afb1a486d39ab0a8f0766
+size 14667

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f27425f69532dc43059551c6d45d8a335d0bb05597418722a40d10d9af2d949
+oid sha256:9401c090d392ec1ff34ad41e4ef3c61b08f5c60281917feed41f5346076fd8b4
 size 4984