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: wav2vec2-common_voice-en-demo
-  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: 1.0023633677991137
 ---
 
 <!-- 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. -->
 
 # wav2vec2-common_voice-en-demo
 
-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: 20.2294
+- Wer: 1.0024
 
 ## Model description
 

adapter.eng.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f16202c0de9c8feeaa1cf336a6630fc754a6ed13dca6fb50a2468e0c7c3f94d2
+oid sha256:a7fc12bdeecd5b36ad6a1fa85f00caaa02034ef6c105b1b27ac58abcaf9b6232
 size 3918936

all_results.json

@@ -1,15 +1,15 @@
 {
     "epoch": 1.0,
-    "eval_loss": 20.233524322509766,
-    "eval_runtime": 167.9773,
+    "eval_loss": 20.229398727416992,
+    "eval_runtime": 167.7396,
     "eval_samples": 2416,
-    "eval_samples_per_second": 14.383,
-    "eval_steps_per_second": 1.798,
-    "eval_wer": 1.0018709995076318,
+    "eval_samples_per_second": 14.403,
+    "eval_steps_per_second": 1.8,
+    "eval_wer": 1.0023633677991137,
     "total_flos": 6.105598680744346e+17,
-    "train_loss": 18.518729795258622,
-    "train_runtime": 625.4328,
+    "train_loss": 18.50860385237069,
+    "train_runtime": 615.4894,
     "train_samples": 4630,
-    "train_samples_per_second": 7.403,
-    "train_steps_per_second": 0.232
+    "train_samples_per_second": 7.522,
+    "train_steps_per_second": 0.236
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
-    "eval_loss": 20.233524322509766,
-    "eval_runtime": 167.9773,
+    "eval_loss": 20.229398727416992,
+    "eval_runtime": 167.7396,
     "eval_samples": 2416,
-    "eval_samples_per_second": 14.383,
-    "eval_steps_per_second": 1.798,
-    "eval_wer": 1.0018709995076318
+    "eval_samples_per_second": 14.403,
+    "eval_steps_per_second": 1.8,
+    "eval_wer": 1.0023633677991137
 }

runs/May25_12-14-50_d77941dfb6d4/events.out.tfevents.1716640249.d77941dfb6d4.7672.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14e3b90d7609ffd19c1601f164c7d0567cec9fb0960beeea80ea82f191a515c4
+size 406

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 6.105598680744346e+17,
-    "train_loss": 18.518729795258622,
-    "train_runtime": 625.4328,
+    "train_loss": 18.50860385237069,
+    "train_runtime": 615.4894,
     "train_samples": 4630,
-    "train_samples_per_second": 7.403,
-    "train_steps_per_second": 0.232
+    "train_samples_per_second": 7.522,
+    "train_steps_per_second": 0.236
 }

trainer_state.json

@@ -10,21 +10,21 @@
   "log_history": [
     {
       "epoch": 0.6896551724137931,
-      "eval_loss": 21.947891235351562,
-      "eval_runtime": 168.4847,
-      "eval_samples_per_second": 14.34,
-      "eval_steps_per_second": 1.792,
-      "eval_wer": 1.0003446578040374,
+      "eval_loss": 21.9151554107666,
+      "eval_runtime": 164.601,
+      "eval_samples_per_second": 14.678,
+      "eval_steps_per_second": 1.835,
+      "eval_wer": 1.0004431314623339,
       "step": 100
     },
     {
       "epoch": 1.0,
       "step": 145,
       "total_flos": 6.105598680744346e+17,
-      "train_loss": 18.518729795258622,
-      "train_runtime": 625.4328,
-      "train_samples_per_second": 7.403,
-      "train_steps_per_second": 0.232
+      "train_loss": 18.50860385237069,
+      "train_runtime": 615.4894,
+      "train_samples_per_second": 7.522,
+      "train_steps_per_second": 0.236
     }
   ],
   "logging_steps": 500,