End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: mit
 base_model: facebook/w2v-bert-2.0
 tags:
+- automatic-speech-recognition
+- CLEAR-Global/luo_19h
 - generated_from_trainer
 metrics:
 - wer
@@ -16,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # w2v-bert-2.0-luo_cv_fleurs_19h-v3
 
-This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
+This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the CLEAR-GLOBAL/LUO_19H - NA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4149
-- Wer: 0.3051
-- Cer: 0.0905
+- Loss: 0.2850
+- Wer: 0.3100
+- Cer: 0.0950
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 58.44155844155844,
+    "eval_cer": 0.09501244879929323,
+    "eval_loss": 0.28501734137535095,
+    "eval_runtime": 9.0702,
+    "eval_samples": 101,
+    "eval_samples_per_second": 11.135,
+    "eval_steps_per_second": 0.441,
+    "eval_wer": 0.3099647266313933,
+    "total_flos": 1.2252419622219763e+20,
+    "train_loss": 0.5878761944652457,
+    "train_runtime": 19643.9285,
+    "train_samples": 9856,
+    "train_samples_per_second": 325.8,
+    "train_steps_per_second": 5.091
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 58.44155844155844,
+    "eval_cer": 0.09501244879929323,
+    "eval_loss": 0.28501734137535095,
+    "eval_runtime": 9.0702,
+    "eval_samples": 101,
+    "eval_samples_per_second": 11.135,
+    "eval_steps_per_second": 0.441,
+    "eval_wer": 0.3099647266313933
+}

runs/Apr12_14-19-56_synvoices-single-a100/events.out.tfevents.1744487975.synvoices-single-a100.86658.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a79201ba7bfccb8ab63d87ba3383e0477616cd1112c68b7d9e96db47c6ea5ae
+size 453

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 58.44155844155844,
+    "total_flos": 1.2252419622219763e+20,
+    "train_loss": 0.5878761944652457,
+    "train_runtime": 19643.9285,
+    "train_samples": 9856,
+    "train_samples_per_second": 325.8,
+    "train_steps_per_second": 5.091
+}