End of training

README.md

@@ -1,6 +1,4 @@
 ---
-license: apache-2.0
-base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
 model-index:
@@ -13,15 +11,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-base-minilibrispeech
 
-This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 0.5513
-- eval_wer: 0.1824
-- eval_runtime: 8.0543
-- eval_samples_per_second: 13.533
-- eval_steps_per_second: 1.738
-- epoch: 30.61
-- step: 7500
+This model was trained from scratch on the None dataset.
 
 ## Model description
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/wav2vec2-base",
+  "_name_or_path": "/content/3funnn/wav2vec2-base-minilibrispeech/checkpoint-5500",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40329d946a4504caeb261bad37c788873cf25955888cd927520edddfc7ab8e06
+oid sha256:d449e44bb2560db58b0ac4a7430c81d442743f3a9c04ddb5fc954ac1f2d94991
 size 377611120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aadf006601d4796f42af144e5ee59bf3e8035d9f32c164ffdb90608b04991433
+oid sha256:7cc85f58d69b38270b4a23e113b56a808357860188221987b164a65b5a00dd88
 size 4920