Model save

README.md

@@ -1,8 +1,5 @@
 ---
-base_model: wav2vec2-pretrained-base-hyperVQ
 tags:
-- automatic-speech-recognition
-- timit_asr
 - generated_from_trainer
 datasets:
 - timit_asr
@@ -15,15 +12,15 @@ model-index:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: TIMIT_ASR - NA
+      name: timit_asr
       type: timit_asr
       config: clean
       split: test
-      args: 'Config: na, Training split: train, Eval split: test'
+      args: clean
     metrics:
     - name: Wer
       type: wer
-      value: 0.5904486251808972
+      value: 0.9993108676176694
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +28,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-base-hyperVQ-timit-fine-tuned
 
-This model is a fine-tuned version of [wav2vec2-pretrained-base-hyperVQ](https://huggingface.co/wav2vec2-pretrained-base-hyperVQ) on the TIMIT_ASR - NA dataset.
+This model was trained from scratch on the timit_asr dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6917
-- Wer: 0.5904
+- Loss: 3.3628
+- Wer: 0.9993
 
 ## Model description
 
@@ -66,8 +63,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.6057        | 10.0  | 1450 | 0.6450          | 0.6166 |
-| 0.327         | 20.0  | 2900 | 0.6917          | 0.5904 |
+| 3.2725        | 10.0  | 1450 | 3.4699          | 1.0006 |
+| 3.1682        | 20.0  | 2900 | 3.3628          | 0.9993 |
 
 
 ### Framework versions