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_250h
 - 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_250h
 
-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_250H - NA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2544
-- Wer: 0.3309
-- Cer: 0.1892
+- Loss: 0.2333
+- Wer: 0.3302
+- Cer: 0.1886
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 24.58100558659218,
+    "eval_cer": 0.188646307267629,
+    "eval_loss": 0.23326905071735382,
+    "eval_runtime": 28.3972,
+    "eval_samples": 4538,
+    "eval_samples_per_second": 159.805,
+    "eval_steps_per_second": 0.528,
+    "eval_wer": 0.3301583754643725,
+    "total_flos": 6.74209699445166e+20,
+    "train_loss": 0.27749355743317444,
+    "train_runtime": 43212.1061,
+    "train_samples": 286371,
+    "train_samples_per_second": 662.71,
+    "train_steps_per_second": 2.071
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 24.58100558659218,
+    "eval_cer": 0.188646307267629,
+    "eval_loss": 0.23326905071735382,
+    "eval_runtime": 28.3972,
+    "eval_samples": 4538,
+    "eval_samples_per_second": 159.805,
+    "eval_steps_per_second": 0.528,
+    "eval_wer": 0.3301583754643725
+}

runs/Apr24_08-23-31_synvoices-hausa-2/events.out.tfevents.1745527336.synvoices-hausa-2.56672.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec7f0cc1382f93ec1e0c1a521d278c3c3ed5d1b789a947cf4feec0e1b420e4d
+size 460

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 24.58100558659218,
+    "total_flos": 6.74209699445166e+20,
+    "train_loss": 0.27749355743317444,
+    "train_runtime": 43212.1061,
+    "train_samples": 286371,
+    "train_samples_per_second": 662.71,
+    "train_steps_per_second": 2.071
+}