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_579_993h_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_579_993h_yourtts
 
-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_579_993H_YOURTTS - NA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2262
-- Wer: 0.3255
-- Cer: 0.1875
+- Loss: 0.2249
+- Wer: 0.3234
+- Cer: 0.1866
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 7.222914072229141,
+    "eval_cer": 0.18664964594721395,
+    "eval_loss": 0.22493159770965576,
+    "eval_runtime": 29.1657,
+    "eval_samples": 4538,
+    "eval_samples_per_second": 155.594,
+    "eval_steps_per_second": 0.514,
+    "eval_wer": 0.3233987877433591,
+    "total_flos": 1.2263871875397976e+21,
+    "train_loss": 0.18328844010874887,
+    "train_runtime": 80378.1883,
+    "train_samples": 1284731,
+    "train_samples_per_second": 255.737,
+    "train_steps_per_second": 0.799
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 7.222914072229141,
+    "eval_cer": 0.18664964594721395,
+    "eval_loss": 0.22493159770965576,
+    "eval_runtime": 29.1657,
+    "eval_samples": 4538,
+    "eval_samples_per_second": 155.594,
+    "eval_steps_per_second": 0.514,
+    "eval_wer": 0.3233987877433591
+}

runs/May31_09-36-14_hausa-synvoices-yourtts/events.out.tfevents.1748770391.hausa-synvoices-yourtts.57895.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1866d97fdad2012563e8bf7af6e1e1aa05a8d67830a23a996ff07d9dd783593
+size 460

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.222914072229141,
+    "total_flos": 1.2263871875397976e+21,
+    "train_loss": 0.18328844010874887,
+    "train_runtime": 80378.1883,
+    "train_samples": 1284731,
+    "train_samples_per_second": 255.737,
+    "train_steps_per_second": 0.799
+}