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_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_34_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_34_34H - NA dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4180
-- Wer: 0.4121
-- Cer: 0.1168
+- Loss: 0.3084
+- Wer: 0.3910
+- Cer: 0.1127
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 25.831024930747922,
+    "eval_cer": 0.11270964564377738,
+    "eval_loss": 0.3083978593349457,
+    "eval_runtime": 17.2653,
+    "eval_samples": 304,
+    "eval_samples_per_second": 17.608,
+    "eval_steps_per_second": 0.579,
+    "eval_wer": 0.39102072141212585,
+    "total_flos": 1.8828835451512226e+20,
+    "train_loss": 0.3484456565128265,
+    "train_runtime": 27570.5866,
+    "train_samples": 34643,
+    "train_samples_per_second": 232.131,
+    "train_steps_per_second": 3.627
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 25.831024930747922,
+    "eval_cer": 0.11270964564377738,
+    "eval_loss": 0.3083978593349457,
+    "eval_runtime": 17.2653,
+    "eval_samples": 304,
+    "eval_samples_per_second": 17.608,
+    "eval_steps_per_second": 0.579,
+    "eval_wer": 0.39102072141212585
+}

runs/Apr19_14-56-49_synvoices-a100-chichewa/events.out.tfevents.1745103911.synvoices-a100-chichewa.80198.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2aaa7c116f66257e6e8b08478f9dc51cc02a7494ce8c07e4fe9a1f51f861bc2
+size 453

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 25.831024930747922,
+    "total_flos": 1.8828835451512226e+20,
+    "train_loss": 0.3484456565128265,
+    "train_runtime": 27570.5866,
+    "train_samples": 34643,
+    "train_samples_per_second": 232.131,
+    "train_steps_per_second": 3.627
+}