End of training

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 base_model: facebook/hubert-large-ll60k
 tags:
+- automatic-speech-recognition
+- macabdul9/librispeech-hubert-discrete-tokens
 - generated_from_trainer
 metrics:
 - wer
@@ -15,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # hubert-large-ll60k-librispeech-multi-gpu
 
-This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on an unknown dataset.
+This model is a fine-tuned version of [facebook/hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k) on the MACABDUL9/LIBRISPEECH-HUBERT-DISCRETE-TOKENS - NA dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0616
 - Wer: 0.0460

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 0.06156753748655319,
+    "eval_runtime": 183.6191,
+    "eval_samples": 2642,
+    "eval_samples_per_second": 14.388,
+    "eval_steps_per_second": 0.452,
+    "eval_wer": 0.04597381991273304,
+    "train_loss": 0.13451409900581351,
+    "train_runtime": 46616.5397,
+    "train_samples": 28538,
+    "train_samples_per_second": 2.449,
+    "train_steps_per_second": 0.306
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 0.06156753748655319,
+    "eval_runtime": 183.6191,
+    "eval_samples": 2642,
+    "eval_samples_per_second": 14.388,
+    "eval_steps_per_second": 0.452,
+    "eval_wer": 0.04597381991273304
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.13451409900581351,
+    "train_runtime": 46616.5397,
+    "train_samples": 28538,
+    "train_samples_per_second": 2.449,
+    "train_steps_per_second": 0.306
+}