End of training

README.md

@@ -1,7 +1,11 @@
 ---
+language:
+- en
 license: mit
 base_model: ylacombe/wav2vec2-bert-CV16-en-libri
 tags:
+- automatic-speech-recognition
+- mozilla-foundation/common_voice_16_0
 - generated_from_trainer
 metrics:
 - wer
@@ -15,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-bert-CV16-en-libri-cv
 
-This model is a fine-tuned version of [ylacombe/wav2vec2-bert-CV16-en-libri](https://huggingface.co/ylacombe/wav2vec2-bert-CV16-en-libri) on the None dataset.
+This model is a fine-tuned version of [ylacombe/wav2vec2-bert-CV16-en-libri](https://huggingface.co/ylacombe/wav2vec2-bert-CV16-en-libri) on the MOZILLA-FOUNDATION/COMMON_VOICE_16_0 - EN dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2169
-- Wer: 0.1351
-- Cer: 0.0524
+- Loss: 0.2168
+- Wer: 0.1352
+- Cer: 0.0525
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_cer": 0.05247981945610226,
+    "eval_loss": 0.21681834757328033,
+    "eval_runtime": 275.4251,
+    "eval_samples": 16370,
+    "eval_samples_per_second": 59.435,
+    "eval_steps_per_second": 1.652,
+    "eval_wer": 0.13516125451375513,
+    "train_loss": 0.13587924622752628,
+    "train_runtime": 175088.5296,
+    "train_samples": 1104466,
+    "train_samples_per_second": 31.54,
+    "train_steps_per_second": 0.292
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_cer": 0.05247981945610226,
+    "eval_loss": 0.21681834757328033,
+    "eval_runtime": 275.4251,
+    "eval_samples": 16370,
+    "eval_samples_per_second": 59.435,
+    "eval_steps_per_second": 1.652,
+    "eval_wer": 0.13516125451375513
+}

runs/Jan16_16-58-34_vorace/events.out.tfevents.1705601589.vorace.518965.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa31b26d7381fa3dee95810f88241b5bd572206f3fa8fc1afe249593b94ce24
+size 412

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.13587924622752628,
+    "train_runtime": 175088.5296,
+    "train_samples": 1104466,
+    "train_samples_per_second": 31.54,
+    "train_steps_per_second": 0.292
+}