End of training

README.md

@@ -1,13 +1,33 @@
 ---
+language:
+- hi
 license: apache-2.0
 base_model: facebook/wav2vec2-large-xlsr-53
 tags:
+- automatic-speech-recognition
+- mozilla-foundation/common_voice_15_0
+- mms
 - generated_from_trainer
 datasets:
 - common_voice_15_0
+metrics:
+- wer
 model-index:
 - name: Output
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: MOZILLA-FOUNDATION/COMMON_VOICE_15_0 - HI
+      type: common_voice_15_0
+      config: hi
+      split: validation
+      args: 'Config: hi, Training split: train, Eval split: validation'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 1.0016248153618907
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +35,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Output
 
-This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice_15_0 dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MOZILLA-FOUNDATION/COMMON_VOICE_15_0 - HI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 20.2289
+- Wer: 1.0016
 
 ## Model description
 

adapter.eng.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf6d26aecc1c334309cc0db4283457295ab01917747eade8ebe337512b72ada
+oid sha256:9ebd4b5a652b53ee5ee6bc8c051c5e01ddf466dc4cc7dc21182cfaaf911023d5
 size 3918936

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 1.0,
-    "eval_loss": 20.135631561279297,
-    "eval_runtime": 1215.354,
+    "eval_loss": 20.228919982910156,
+    "eval_runtime": 119.2704,
     "eval_samples": 2416,
-    "eval_samples_per_second": 1.988,
-    "eval_steps_per_second": 0.248,
-    "eval_wer": 1.0123092072870508,
+    "eval_samples_per_second": 20.256,
+    "eval_steps_per_second": 2.532,
+    "eval_wer": 1.0016248153618907,
     "total_flos": 6.105598680744346e+17,
-    "train_loss": 18.478419652478447,
-    "train_runtime": 6075.5306,
+    "train_loss": 18.507504377693966,
+    "train_runtime": 329.6848,
     "train_samples": 4630,
-    "train_samples_per_second": 0.762,
-    "train_steps_per_second": 0.024
+    "train_samples_per_second": 14.044,
+    "train_steps_per_second": 0.44
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
-    "eval_loss": 20.135631561279297,
-    "eval_runtime": 1215.354,
+    "eval_loss": 20.228919982910156,
+    "eval_runtime": 119.2704,
     "eval_samples": 2416,
-    "eval_samples_per_second": 1.988,
-    "eval_steps_per_second": 0.248,
-    "eval_wer": 1.0123092072870508
+    "eval_samples_per_second": 20.256,
+    "eval_steps_per_second": 2.532,
+    "eval_wer": 1.0016248153618907
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 6.105598680744346e+17,
-    "train_loss": 18.478419652478447,
-    "train_runtime": 6075.5306,
+    "train_loss": 18.507504377693966,
+    "train_runtime": 329.6848,
     "train_samples": 4630,
-    "train_samples_per_second": 0.762,
-    "train_steps_per_second": 0.024
+    "train_samples_per_second": 14.044,
+    "train_steps_per_second": 0.44
 }

trainer_state.json

@@ -10,21 +10,21 @@
   "log_history": [
     {
       "epoch": 0.6896551724137931,
-      "eval_loss": 21.880786895751953,
-      "eval_runtime": 1223.8571,
-      "eval_samples_per_second": 1.974,
-      "eval_steps_per_second": 0.247,
-      "eval_wer": 1.000246184145741,
+      "eval_loss": 21.916179656982422,
+      "eval_runtime": 84.3206,
+      "eval_samples_per_second": 28.653,
+      "eval_steps_per_second": 3.582,
+      "eval_wer": 1.0002954209748893,
       "step": 100
     },
     {
       "epoch": 1.0,
       "step": 145,
       "total_flos": 6.105598680744346e+17,
-      "train_loss": 18.478419652478447,
-      "train_runtime": 6075.5306,
-      "train_samples_per_second": 0.762,
-      "train_steps_per_second": 0.024
+      "train_loss": 18.507504377693966,
+      "train_runtime": 329.6848,
+      "train_samples_per_second": 14.044,
+      "train_steps_per_second": 0.44
     }
   ],
   "logging_steps": 500,