End of training

README.md

@@ -1,6 +1,10 @@
 ---
+language:
+- en
 base_model: ylacombe/w2v-bert-2.0
 tags:
+- automatic-speech-recognition
+- mozilla-foundation/common_voice_16_0
 - generated_from_trainer
 metrics:
 - wer
@@ -14,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-bert-CV16-en
 
-This model is a fine-tuned version of [ylacombe/w2v-bert-2.0](https://huggingface.co/ylacombe/w2v-bert-2.0) on the None dataset.
+This model is a fine-tuned version of [ylacombe/w2v-bert-2.0](https://huggingface.co/ylacombe/w2v-bert-2.0) on the MOZILLA-FOUNDATION/COMMON_VOICE_16_0 - EN dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.2427
 - Wer: 0.1455

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_cer": 0.05799117166237736,
+    "eval_loss": 0.24269694089889526,
+    "eval_runtime": 274.167,
+    "eval_samples": 16370,
+    "eval_samples_per_second": 59.708,
+    "eval_steps_per_second": 1.66,
+    "eval_wer": 0.14549146875795824,
+    "train_loss": 0.19391593228424958,
+    "train_runtime": 209626.9679,
+    "train_samples": 1104466,
+    "train_samples_per_second": 15.806,
+    "train_steps_per_second": 0.439
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_cer": 0.05799117166237736,
+    "eval_loss": 0.24269694089889526,
+    "eval_runtime": 274.167,
+    "eval_samples": 16370,
+    "eval_samples_per_second": 59.708,
+    "eval_steps_per_second": 1.66,
+    "eval_wer": 0.14549146875795824
+}

runs/Jan13_00-37-49_vorace/events.out.tfevents.1705316297.vorace.290722.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d170ea82f1e10a3aafaaf810f97a8b2ad1180d1cfa91bd852ecea45ed1df8c69
+size 412

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.19391593228424958,
+    "train_runtime": 209626.9679,
+    "train_samples": 1104466,
+    "train_samples_per_second": 15.806,
+    "train_steps_per_second": 0.439
+}