End of training

README.md

@@ -1,28 +1,28 @@
 ---
 license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
 tags:
 - generated_from_trainer
-base_model: facebook/wav2vec2-large-xlsr-53
 datasets:
-- xtreme_s
+- common_voice_13_0
 metrics:
 - wer
 model-index:
 - name: wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod11
   results:
   - task:
-      type: automatic-speech-recognition
       name: Automatic Speech Recognition
+      type: automatic-speech-recognition
     dataset:
-      name: xtreme_s
-      type: xtreme_s
-      config: fleurs.id_id
+      name: common_voice_13_0
+      type: common_voice_13_0
+      config: id
       split: test
-      args: fleurs.id_id
+      args: id
     metrics:
-    - type: wer
-      value: 1.0
-      name: Wer
+    - name: Wer
+      type: wer
+      value: 0.9777378318584071
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-XLS-R-Fleurs-demo-google-colab-Ezra_William_Prod11
 
-This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the xtreme_s dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3184
-- Wer: 1.0
+- Loss: 1.3207
+- Wer: 0.9777
 
 ## Model description
 
@@ -58,28 +58,23 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer |
-|:-------------:|:-----:|:----:|:---------------:|:---:|
-| 3.6308        | 1.0   | 126  | 2.8604          | 1.0 |
-| 2.8784        | 2.0   | 252  | 2.8477          | 1.0 |
-| 2.8707        | 3.0   | 378  | 2.8556          | 1.0 |
-| 2.8589        | 4.0   | 504  | 2.8471          | 1.0 |
-| 2.8518        | 5.0   | 630  | 2.8402          | 1.0 |
-| 2.8472        | 6.0   | 756  | 2.8495          | 1.0 |
-| 2.8414        | 7.0   | 882  | 2.8303          | 1.0 |
-| 2.8215        | 8.0   | 1008 | 2.7800          | 1.0 |
-| 2.7687        | 9.0   | 1134 | 2.6640          | 1.0 |
-| 2.5326        | 10.0  | 1260 | 2.3184          | 1.0 |
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| No log        | 1.0   | 464  | 2.8781          | 1.0    |
+| 3.005         | 2.0   | 928  | 2.5395          | 1.0    |
+| 2.7477        | 3.0   | 1392 | 1.6528          | 0.9993 |
+| 1.9398        | 4.0   | 1856 | 1.3991          | 0.9854 |
+| 1.4528        | 5.0   | 2320 | 1.3207          | 0.9777 |
 
 
 ### Framework versions
 
-- Transformers 4.39.2
+- Transformers 4.39.3
 - Pytorch 2.2.2+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41620bdc64a88239cd1c28386680c304a240c1ccf039397eeeaebdb4eb06f508
+oid sha256:f35543c96d7158b5c611523dc7ba67bc89ba9c12df010efd1ffd75cb2bc83ecd
 size 1261991980

runs/Apr06_03-17-52_91f2b20a926f/events.out.tfevents.1712373719.91f2b20a926f.243.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83dcc11f6c8d46042ecc28aa7b4eb4931118591f5e1dd0d80d8c1e5a4ef825e
-size 8511
+oid sha256:da6995f83054814a2421a5d5ffa44ede78ae3333a099891edd74de200fb7de99
+size 9183