Model save

README.md

@@ -1,28 +1,13 @@
 ---
 license: apache-2.0
+base_model: Amadkour/wav2vec2-large-xls-r-300m-tr-softkour
 tags:
 - generated_from_trainer
-base_model: facebook/wav2vec2-xls-r-300m
 datasets:
 - common_voice_11_0
-metrics:
-- wer
 model-index:
 - name: wav2vec2-large-xls-r-300m-tr-softkour
-  results:
-  - task:
-      type: automatic-speech-recognition
-      name: Automatic Speech Recognition
-    dataset:
-      name: common_voice_11_0
-      type: common_voice_11_0
-      config: ar
-      split: test
-      args: ar
-    metrics:
-    - type: wer
-      value: 0.6080256761575855
-      name: Wer
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-large-xls-r-300m-tr-softkour
 
-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_11_0 dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.6249
-- Wer: 0.6080
+This model is a fine-tuned version of [Amadkour/wav2vec2-large-xls-r-300m-tr-softkour](https://huggingface.co/Amadkour/wav2vec2-large-xls-r-300m-tr-softkour) on the common_voice_11_0 dataset.
 
 ## Model description
 
@@ -65,11 +47,6 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| 6.582         | 0.33  | 400  | 3.3382          | 0.9991 |
-| 2.0467        | 0.67  | 800  | 0.8908          | 0.7406 |
-| 0.8479        | 1.0   | 1200 | 0.6249          | 0.6080 |
 
 
 ### Framework versions

config.json

@@ -78,7 +78,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 96,
+  "pad_token_id": 44,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -104,6 +104,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
   "use_weighted_layer_sum": false,
-  "vocab_size": 99,
+  "vocab_size": 47,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fe71be0cb4afe46b3faf6bc9f2dbcc2947bbe0f76a1b81ce4ccaa756a74e493
-size 1262213380
+oid sha256:91cecb65a4fee9d3b611fe0ceb7fce575e8a3dae1b3733e8bb0056ab6cd42da7
+size 1262000180

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3af72477c1da73c58640470c5fc258e6dfc9ded98aec2944ea0c0eb9871440c
+oid sha256:e30d5500c11e420521b208796e48bc2c2fe8fa5edc4cb41e3c72f0f06362dd70
 size 4920