wav2vec2-large-xls-r-300m-hungarian-colab

README.md

@@ -16,6 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 # wav2vec2-large-xls-r-300m-hungarian-colab-finetuned
 
 This model is a fine-tuned version of [facebook/wav2vec2-lv-60-espeak-cv-ft](https://huggingface.co/facebook/wav2vec2-lv-60-espeak-cv-ft) on the voxpopuli dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 17417.8594
+- eval_wer: 0.9967
+- eval_runtime: 127.2862
+- eval_samples_per_second: 3.928
+- eval_steps_per_second: 0.495
+- step: 0
 
 ## Model description
 
@@ -43,13 +50,9 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 50
+- num_epochs: 30
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
 - Transformers 4.35.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d2c25c38d58f77524b53a92f83b670221406f25b4040de5402836e0a7d0077a
+oid sha256:4a91430d53b38ea91d19d3773197f92046bee5467bc3fb62670a0dfdb1c49188
 size 1263414696

runs/Nov26_10-43-29_3bcc1816d3f4/events.out.tfevents.1700995542.3bcc1816d3f4.482.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8693327cb849efb9df6bc96154be9d51fedc3b4cbba10bf0db7a6488c69ea2d
+size 341

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:371e014030c8f924747485d063299d2e94f273d64d2b87c5fbd60717dc5cfdaf
+oid sha256:9baaeda56d7cfa362feea7df1f679946d983e11ca7e90e867c526dd00c0b8308
 size 4600