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/hausa_250_250h_yourtts
 - generated_from_trainer
 metrics:
 - wer
@@ -16,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # w2v-bert-2.0-hausa_250_250h_yourtts-v2
 
-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/HAUSA_250_250H_YOURTTS - NA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2410
-- Wer: 0.3277
-- Cer: 0.1881
+- Loss: 0.2388
+- Wer: 0.3314
+- Cer: 0.1898
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 18.063583815028903,
+    "eval_cer": 0.18978647725660916,
+    "eval_loss": 0.23882515728473663,
+    "eval_runtime": 28.7606,
+    "eval_samples": 4538,
+    "eval_samples_per_second": 157.785,
+    "eval_steps_per_second": 0.522,
+    "eval_wer": 0.3313594592329823,
+    "total_flos": 9.789083817144788e+20,
+    "train_loss": 0.21370420854050667,
+    "train_runtime": 64430.5867,
+    "train_samples": 442800,
+    "train_samples_per_second": 343.626,
+    "train_steps_per_second": 1.074
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 18.063583815028903,
+    "eval_cer": 0.18978647725660916,
+    "eval_loss": 0.23882515728473663,
+    "eval_runtime": 28.7606,
+    "eval_samples": 4538,
+    "eval_samples_per_second": 157.785,
+    "eval_steps_per_second": 0.522,
+    "eval_wer": 0.3313594592329823
+}

runs/May28_21-42-57_synvoices-hausa-yourtss/events.out.tfevents.1748533487.synvoices-hausa-yourtss.57965.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94179c1763b067517a78e3e70ca5f78ba3ef56d76aaad05be2b77ee1616e66eb
+size 460

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 18.063583815028903,
+    "total_flos": 9.789083817144788e+20,
+    "train_loss": 0.21370420854050667,
+    "train_runtime": 64430.5867,
+    "train_samples": 442800,
+    "train_samples_per_second": 343.626,
+    "train_steps_per_second": 1.074
+}