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: 1.0123092072870508
 ---
 
 <!-- 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: 20.1356
+- Wer: 1.0123
 
 ## Model description
 

adapter.eng.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf6d26aecc1c334309cc0db4283457295ab01917747eade8ebe337512b72ada
+size 3918936

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 20.135631561279297,
+    "eval_runtime": 1215.354,
+    "eval_samples": 2416,
+    "eval_samples_per_second": 1.988,
+    "eval_steps_per_second": 0.248,
+    "eval_wer": 1.0123092072870508,
+    "total_flos": 6.105598680744346e+17,
+    "train_loss": 18.478419652478447,
+    "train_runtime": 6075.5306,
+    "train_samples": 4630,
+    "train_samples_per_second": 0.762,
+    "train_steps_per_second": 0.024
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 20.135631561279297,
+    "eval_runtime": 1215.354,
+    "eval_samples": 2416,
+    "eval_samples_per_second": 1.988,
+    "eval_steps_per_second": 0.248,
+    "eval_wer": 1.0123092072870508
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 6.105598680744346e+17,
+    "train_loss": 18.478419652478447,
+    "train_runtime": 6075.5306,
+    "train_samples": 4630,
+    "train_samples_per_second": 0.762,
+    "train_steps_per_second": 0.024
+}

trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 145,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "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,
+      "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 145,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.105598680744346e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}