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/chichewa_34h
 - generated_from_trainer
 metrics:
 - wer
@@ -16,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # w2v-bert-2.0-chichewa_34h
 
-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/CHICHEWA_34H - NA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4660
-- Wer: 0.3855
-- Cer: 0.1101
+- Loss: 0.3389
+- Wer: 0.4045
+- Cer: 0.1148
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 50.563380281690144,
+    "eval_cer": 0.11475749799103092,
+    "eval_loss": 0.33892425894737244,
+    "eval_runtime": 16.645,
+    "eval_samples": 304,
+    "eval_samples_per_second": 18.264,
+    "eval_steps_per_second": 0.601,
+    "eval_wer": 0.4044512663085188,
+    "total_flos": 1.839618674746837e+20,
+    "train_loss": 0.4364977639418147,
+    "train_runtime": 29158.6875,
+    "train_samples": 11352,
+    "train_samples_per_second": 219.489,
+    "train_steps_per_second": 3.43
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 50.563380281690144,
+    "eval_cer": 0.11475749799103092,
+    "eval_loss": 0.33892425894737244,
+    "eval_runtime": 16.645,
+    "eval_samples": 304,
+    "eval_samples_per_second": 18.264,
+    "eval_steps_per_second": 0.601,
+    "eval_wer": 0.4044512663085188
+}

runs/Apr18_14-58-51_synvoices-a100-chichewa/events.out.tfevents.1745018236.synvoices-a100-chichewa.4022.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93b0717d423ede92c6047367b548b0aa866bd65c533f3cb20e44e5360794ae06
+size 453

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 50.563380281690144,
+    "total_flos": 1.839618674746837e+20,
+    "train_loss": 0.4364977639418147,
+    "train_runtime": 29158.6875,
+    "train_samples": 11352,
+    "train_samples_per_second": 219.489,
+    "train_steps_per_second": 3.43
+}