End of training

README.md

@@ -4,11 +4,24 @@ license: apache-2.0
 base_model: openai/whisper-base
 tags:
 - generated_from_trainer
+datasets:
+- razhan/DOLMA-speech
 metrics:
 - wer
 model-index:
 - name: whisper-base-lki
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: razhan/DOLMA-speech laki_kurdish
+      type: razhan/DOLMA-speech
+      args: laki_kurdish
+    metrics:
+    - name: Wer
+      type: wer
+      value: 1.008409596834034
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -16,7 +29,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-base-lki
 
-This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
+This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the razhan/DOLMA-speech laki_kurdish dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.8590
 - Wer: 1.0084

all_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 5.0,
-    "eval_cer": 0.5701466189378709,
-    "eval_loss": 4.024605751037598,
-    "eval_runtime": 36.7376,
+    "eval_cer": 0.5075761290638945,
+    "eval_loss": 2.859005928039551,
+    "eval_runtime": 35.745,
     "eval_samples": 313,
-    "eval_samples_per_second": 8.52,
-    "eval_steps_per_second": 0.054,
-    "eval_wer": 1.113034875092753,
+    "eval_samples_per_second": 8.756,
+    "eval_steps_per_second": 0.056,
+    "eval_wer": 1.008409596834034,
     "total_flos": 2.4906238324113408e+17,
-    "train_loss": 4.0161895751953125,
-    "train_runtime": 411.106,
+    "train_loss": 3.8715896606445312,
+    "train_runtime": 410.1322,
     "train_samples": 755,
-    "train_samples_per_second": 9.183,
+    "train_samples_per_second": 9.204,
     "train_steps_per_second": 0.024
 }

eval_results.json

@@ -1,10 +1,10 @@
 {
     "epoch": 5.0,
-    "eval_cer": 0.5701466189378709,
-    "eval_loss": 4.024605751037598,
-    "eval_runtime": 36.7376,
+    "eval_cer": 0.5075761290638945,
+    "eval_loss": 2.859005928039551,
+    "eval_runtime": 35.745,
     "eval_samples": 313,
-    "eval_samples_per_second": 8.52,
-    "eval_steps_per_second": 0.054,
-    "eval_wer": 1.113034875092753
+    "eval_samples_per_second": 8.756,
+    "eval_steps_per_second": 0.056,
+    "eval_wer": 1.008409596834034
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 5.0,
     "total_flos": 2.4906238324113408e+17,
-    "train_loss": 4.0161895751953125,
-    "train_runtime": 411.106,
+    "train_loss": 3.8715896606445312,
+    "train_runtime": 410.1322,
     "train_samples": 755,
-    "train_samples_per_second": 9.183,
+    "train_samples_per_second": 9.204,
     "train_steps_per_second": 0.024
 }

trainer_state.json

@@ -12,8 +12,8 @@
       "epoch": 1.0,
       "eval_cer": 0.5721080763006914,
       "eval_loss": 4.031211853027344,
-      "eval_runtime": 36.4445,
-      "eval_samples_per_second": 8.588,
+      "eval_runtime": 36.4676,
+      "eval_samples_per_second": 8.583,
       "eval_steps_per_second": 0.055,
       "eval_wer": 1.1142715805095227,
       "step": 2
@@ -22,8 +22,8 @@
       "epoch": 2.0,
       "eval_cer": 0.5721080763006914,
       "eval_loss": 4.031211853027344,
-      "eval_runtime": 35.8435,
-      "eval_samples_per_second": 8.732,
+      "eval_runtime": 35.8856,
+      "eval_samples_per_second": 8.722,
       "eval_steps_per_second": 0.056,
       "eval_wer": 1.1142715805095227,
       "step": 4
@@ -32,46 +32,46 @@
       "epoch": 3.0,
       "eval_cer": 0.5721080763006914,
       "eval_loss": 4.031211853027344,
-      "eval_runtime": 36.3205,
-      "eval_samples_per_second": 8.618,
+      "eval_runtime": 36.6017,
+      "eval_samples_per_second": 8.552,
       "eval_steps_per_second": 0.055,
       "eval_wer": 1.1142715805095227,
       "step": 6
     },
     {
       "epoch": 4.0,
-      "eval_cer": 0.5720590398666209,
-      "eval_loss": 4.030923366546631,
-      "eval_runtime": 35.7931,
-      "eval_samples_per_second": 8.745,
-      "eval_steps_per_second": 0.056,
-      "eval_wer": 1.1137768983428147,
+      "eval_cer": 0.5898102290001471,
+      "eval_loss": 3.4312429428100586,
+      "eval_runtime": 36.2078,
+      "eval_samples_per_second": 8.645,
+      "eval_steps_per_second": 0.055,
+      "eval_wer": 1.1105614642592134,
       "step": 8
     },
     {
       "epoch": 5.0,
-      "grad_norm": 66.4626693725586,
-      "learning_rate": 4.0000000000000003e-07,
-      "loss": 4.0162,
+      "grad_norm": 36.06775665283203,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 3.8716,
       "step": 10
     },
     {
       "epoch": 5.0,
-      "eval_cer": 0.5701466189378709,
-      "eval_loss": 4.024605751037598,
-      "eval_runtime": 35.8347,
-      "eval_samples_per_second": 8.735,
+      "eval_cer": 0.5075761290638945,
+      "eval_loss": 2.859005928039551,
+      "eval_runtime": 35.6436,
+      "eval_samples_per_second": 8.781,
       "eval_steps_per_second": 0.056,
-      "eval_wer": 1.113034875092753,
+      "eval_wer": 1.008409596834034,
       "step": 10
     },
     {
       "epoch": 5.0,
       "step": 10,
       "total_flos": 2.4906238324113408e+17,
-      "train_loss": 4.0161895751953125,
-      "train_runtime": 411.106,
-      "train_samples_per_second": 9.183,
+      "train_loss": 3.8715896606445312,
+      "train_runtime": 410.1322,
+      "train_samples_per_second": 9.204,
       "train_steps_per_second": 0.024
     }
   ],