End of training

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: facebook/wav2vec2-xls-r-300m
 tags:
 - generated_from_trainer
-base_model: facebook/wav2vec2-large-xlsr-53
 datasets:
 - common_voice_13_0
 metrics:
@@ -11,8 +11,8 @@ model-index:
 - name: wav2vec2-xlsr-53-CV-demo-google-colab-Ezra_William_Prod19
   results:
   - task:
-      type: automatic-speech-recognition
       name: Automatic Speech Recognition
+      type: automatic-speech-recognition
     dataset:
       name: common_voice_13_0
       type: common_voice_13_0
@@ -20,9 +20,9 @@ model-index:
       split: test
       args: id
     metrics:
-    - type: wer
-      value: 0.4921183628318584
-      name: Wer
+    - name: Wer
+      type: wer
+      value: 0.34075405604719766
 ---
 
 <!-- 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-xlsr-53-CV-demo-google-colab-Ezra_William_Prod19
 
-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.
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4839
-- Wer: 0.4921
+- Loss: 0.3575
+- Wer: 0.3408
 
 ## Model description
 
@@ -58,19 +58,22 @@ 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: 6
+- num_epochs: 9
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 2.9477        | 1.0   | 278  | 2.9253          | 1.0    |
-| 2.877         | 2.0   | 556  | 2.8306          | 1.0    |
-| 1.6537        | 3.0   | 834  | 0.8538          | 0.7288 |
-| 0.8469        | 4.0   | 1112 | 0.5611          | 0.5508 |
-| 0.7422        | 5.0   | 1390 | 0.5133          | 0.5045 |
-| 0.6389        | 6.0   | 1668 | 0.4839          | 0.4921 |
+| 2.9583        | 1.0   | 278  | 2.9214          | 1.0    |
+| 2.8606        | 2.0   | 556  | 2.7724          | 1.0    |
+| 1.1528        | 3.0   | 834  | 0.6902          | 0.6319 |
+| 0.7003        | 4.0   | 1112 | 0.4844          | 0.4883 |
+| 0.5853        | 5.0   | 1390 | 0.4030          | 0.4158 |
+| 0.4685        | 6.0   | 1668 | 0.3945          | 0.3838 |
+| 0.4273        | 7.0   | 1946 | 0.3824          | 0.3687 |
+| 0.4116        | 8.0   | 2224 | 0.3643          | 0.3474 |
+| 0.3858        | 9.0   | 2502 | 0.3575          | 0.3408 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e47c4cc76d9d9d29ee3a5dae35729340257dc6eaa0acf0f9da787f9c1b3829
+oid sha256:86ec7bc6539d4760eabe802ca764841659c6d16b5cf22b72d063f0d0e61af2aa
 size 1261991980

runs/Apr30_15-30-08_888461bafdf7/events.out.tfevents.1714491115.888461bafdf7.759.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d383a05ccd32cfbf059f7ce668df182cce3cefbccd4e15d59061dbb54ff657
-size 14060
+oid sha256:3ced587a7b614ab6618f4d84273869cf802dc6d9de994aef9649ffbebe58de12
+size 14732