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_34_136h
 - generated_from_trainer
 metrics:
 - wer
@@ -16,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # w2v-bert-2.0-chichewa_34_136h
 
-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_34_136H - NA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3207
-- Wer: 0.3914
+- Loss: 0.2952
+- Wer: 0.4020
 - Cer: 0.1153
 
 ## Model description

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 11.01591674318947,
+    "eval_cer": 0.11532778598646862,
+    "eval_loss": 0.2951841354370117,
+    "eval_runtime": 17.2103,
+    "eval_samples": 304,
+    "eval_samples_per_second": 17.664,
+    "eval_steps_per_second": 0.581,
+    "eval_wer": 0.40195702225633156,
+    "total_flos": 2.0168463522904673e+20,
+    "train_loss": 0.3225941348490564,
+    "train_runtime": 28037.1099,
+    "train_samples": 104518,
+    "train_samples_per_second": 228.269,
+    "train_steps_per_second": 3.567
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 11.01591674318947,
+    "eval_cer": 0.11532778598646862,
+    "eval_loss": 0.2951841354370117,
+    "eval_runtime": 17.2103,
+    "eval_samples": 304,
+    "eval_samples_per_second": 17.664,
+    "eval_steps_per_second": 0.581,
+    "eval_wer": 0.40195702225633156
+}

runs/Apr20_22-21-15_synvoices-a100-chichewa/events.out.tfevents.1745220023.synvoices-a100-chichewa.146743.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e51b2a60e27bdb4594e7cdb2a61147124aa9705f1e8fba87ae6b7c208443d42
+size 460

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 11.01591674318947,
+    "total_flos": 2.0168463522904673e+20,
+    "train_loss": 0.3225941348490564,
+    "train_runtime": 28037.1099,
+    "train_samples": 104518,
+    "train_samples_per_second": 228.269,
+    "train_steps_per_second": 3.567
+}