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_100_400h_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_100_400h_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_100_400H_YOURTTS - NA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2975
-- Wer: 0.3578
-- Cer: 0.1963
+- Loss: 0.2925
+- Wer: 0.3666
+- Cer: 0.1987
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 7.887817703768624,
+    "eval_cer": 0.1986623460224979,
+    "eval_loss": 0.2925209701061249,
+    "eval_runtime": 27.8568,
+    "eval_samples": 4538,
+    "eval_samples_per_second": 162.905,
+    "eval_steps_per_second": 0.538,
+    "eval_wer": 0.3665819390519818,
+    "total_flos": 4.2501450882947534e+20,
+    "train_loss": 0.31620229341927913,
+    "train_runtime": 27831.3078,
+    "train_samples": 364835,
+    "train_samples_per_second": 655.44,
+    "train_steps_per_second": 2.05
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 7.887817703768624,
+    "eval_cer": 0.1986623460224979,
+    "eval_loss": 0.2925209701061249,
+    "eval_runtime": 27.8568,
+    "eval_samples": 4538,
+    "eval_samples_per_second": 162.905,
+    "eval_steps_per_second": 0.538,
+    "eval_wer": 0.3665819390519818
+}

runs/May30_13-48-03_hausa-synvoices-yourtts/events.out.tfevents.1748641681.hausa-synvoices-yourtts.8542.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:786bbc1f9e83048d9cab78bee792d9f6522db4d850ecaf6511726162a74e8638
+size 453

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 7.887817703768624,
+    "total_flos": 4.2501450882947534e+20,
+    "train_loss": 0.31620229341927913,
+    "train_runtime": 27831.3078,
+    "train_samples": 364835,
+    "train_samples_per_second": 655.44,
+    "train_steps_per_second": 2.05
+}