End of training

README.md

@@ -6,9 +6,24 @@ tags:
 - generated_from_trainer
 datasets:
 - common_voice_17_0
+metrics:
+- wer
 model-index:
 - name: result_data_2-1
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_17_0
+      type: common_voice_17_0
+      config: uk
+      split: test
+      args: uk
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.36626096801585056
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,6 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
 # result_data_2-1
 
 This model is a fine-tuned version of [mouseyy/result_data-1](https://huggingface.co/mouseyy/result_data-1) on the common_voice_17_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2237
+- Wer: 0.3663
+- Cer: 0.1697
 
 ## Model description
 

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 0.009099181073703366,
-    "eval_cer": 0.16934373565855898,
-    "eval_loss": 0.22408190369606018,
-    "eval_runtime": 16.3688,
+    "eval_cer": 0.16967750010430138,
+    "eval_loss": 0.2237045019865036,
+    "eval_runtime": 16.3113,
     "eval_samples": 500,
-    "eval_samples_per_second": 30.546,
-    "eval_steps_per_second": 0.977,
-    "eval_wer": 0.36512878573450325,
+    "eval_samples_per_second": 30.654,
+    "eval_steps_per_second": 0.981,
+    "eval_wer": 0.36626096801585056,
     "total_flos": 7.434959474550374e+16,
-    "train_loss": 0.2877780914306641,
-    "train_runtime": 23.4586,
+    "train_loss": 0.16711194515228273,
+    "train_runtime": 34.1733,
     "train_samples": 35144,
-    "train_samples_per_second": 13.641,
-    "train_steps_per_second": 0.426
+    "train_samples_per_second": 9.364,
+    "train_steps_per_second": 0.293
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 0.009099181073703366,
-    "eval_cer": 0.16934373565855898,
-    "eval_loss": 0.22408190369606018,
-    "eval_runtime": 16.3688,
+    "eval_cer": 0.16967750010430138,
+    "eval_loss": 0.2237045019865036,
+    "eval_runtime": 16.3113,
     "eval_samples": 500,
-    "eval_samples_per_second": 30.546,
-    "eval_steps_per_second": 0.977,
-    "eval_wer": 0.36512878573450325
+    "eval_samples_per_second": 30.654,
+    "eval_steps_per_second": 0.981,
+    "eval_wer": 0.36626096801585056
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 0.009099181073703366,
     "total_flos": 7.434959474550374e+16,
-    "train_loss": 0.2877780914306641,
-    "train_runtime": 23.4586,
+    "train_loss": 0.16711194515228273,
+    "train_runtime": 34.1733,
     "train_samples": 35144,
-    "train_samples_per_second": 13.641,
-    "train_steps_per_second": 0.426
+    "train_samples_per_second": 9.364,
+    "train_steps_per_second": 0.293
 }

trainer_state.json

@@ -12,10 +12,10 @@
       "epoch": 0.009099181073703366,
       "step": 10,
       "total_flos": 7.434959474550374e+16,
-      "train_loss": 0.2877780914306641,
-      "train_runtime": 23.4586,
-      "train_samples_per_second": 13.641,
-      "train_steps_per_second": 0.426
+      "train_loss": 0.16711194515228273,
+      "train_runtime": 34.1733,
+      "train_samples_per_second": 9.364,
+      "train_steps_per_second": 0.293
     }
   ],
   "logging_steps": 100,