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/naijavoices_100h
 - generated_from_trainer
 metrics:
 - wer
@@ -16,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # w2v-bert-2.0-hausa_naijavoices_100h
 
-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/NAIJAVOICES_100H - NA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3840
-- Wer: 0.3541
-- Cer: 0.1939
+- Loss: 0.2644
+- Wer: 0.3398
+- Cer: 0.1916
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 41.899441340782126,
+    "eval_cer": 0.19160311173665892,
+    "eval_loss": 0.264448881149292,
+    "eval_runtime": 24.8051,
+    "eval_samples": 4538,
+    "eval_samples_per_second": 182.947,
+    "eval_steps_per_second": 0.605,
+    "eval_wer": 0.3398229099745817,
+    "total_flos": 4.631234010246996e+20,
+    "train_loss": 0.3056531836404155,
+    "train_runtime": 30334.2374,
+    "train_samples": 114548,
+    "train_samples_per_second": 944.049,
+    "train_steps_per_second": 2.95
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 41.899441340782126,
+    "eval_cer": 0.19160311173665892,
+    "eval_loss": 0.264448881149292,
+    "eval_runtime": 24.8051,
+    "eval_samples": 4538,
+    "eval_samples_per_second": 182.947,
+    "eval_steps_per_second": 0.605,
+    "eval_wer": 0.3398229099745817
+}

runs/Apr23_17-35-24_synvoices-hausa-2/events.out.tfevents.1745460483.synvoices-hausa-2.5480.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c51d39a40408fd39374a1199ac840f23def15f1c08a96ee7bc0eed1a5fd995d
+size 453

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 41.899441340782126,
+    "total_flos": 4.631234010246996e+20,
+    "train_loss": 0.3056531836404155,
+    "train_runtime": 30334.2374,
+    "train_samples": 114548,
+    "train_samples_per_second": 944.049,
+    "train_steps_per_second": 2.95
+}