First model version

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: facebook/wav2vec2-xls-r-300m
+base_model: pinot/wav2vec2-xls-r-300m-ja-phoneme_cv_14_4
 tags:
 - generated_from_trainer
 datasets:
@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 1.0
+      value: 1.0452119589468987
 ---
 
 <!-- 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-300m-ja-phoneme-cv_13_test
 
-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.
+This model is a fine-tuned version of [pinot/wav2vec2-xls-r-300m-ja-phoneme_cv_14_4](https://huggingface.co/pinot/wav2vec2-xls-r-300m-ja-phoneme_cv_14_4) on the common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.4013
-- Wer: 1.0
+- Loss: 3.3902
+- Wer: 1.0452
 
 ## Model description
 
@@ -65,9 +65,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer |
-|:-------------:|:-----:|:----:|:---------------:|:---:|
-| 11.3433       | 3.22  | 500  | 4.4013          | 1.0 |
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 3.4481        | 3.22  | 500  | 3.3902          | 1.0452 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "_name_or_path": "pinot/wav2vec2-xls-r-300m-ja-phoneme_cv_14_4",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6d041e54cc1daadf63589bf71a1d19b09f9ac5607e1a4c6ac6e363d72b7bffc
+oid sha256:79a42233f423e9daba71a9810999a1b53605b892a9ef2edf491385cc96fac05e
 size 1262123245

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4aa44f097b6e19ff8fd5fd85cf670307c38c6dbef41c513ecfbf2463f78d15
+oid sha256:22ae8a232a8da68cd961959e76f39825243f5f92eaad4309d17414b3d609e1e3
 size 4091