End of training

README.md

@@ -1,8 +1,10 @@
 ---
 license: apache-2.0
+base_model: facebook/wav2vec2-xls-r-300m
 tags:
 - generated_from_trainer
-base_model: facebook/wav2vec2-xls-r-300m
+metrics:
+- wer
 model-index:
 - name: xlsr-wav2vec2-model
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # xlsr-wav2vec2-model
 
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7290
+- Wer: 0.4124
 
 ## Model description
 
@@ -40,6 +45,26 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1000
 - num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Wer    |
+|:-------------:|:-------:|:----:|:---------------:|:------:|
+| 7.6084        | 2.1552  | 500  | 3.5347          | 0.9779 |
+| 2.9101        | 4.3103  | 1000 | 3.0371          | 0.9779 |
+| 1.9452        | 6.4655  | 1500 | 0.9591          | 0.7081 |
+| 0.9155        | 8.6207  | 2000 | 0.7387          | 0.5667 |
+| 0.6076        | 10.7759 | 2500 | 0.6607          | 0.5046 |
+| 0.461         | 12.9310 | 3000 | 0.5965          | 0.4689 |
+| 0.3687        | 15.0862 | 3500 | 0.6324          | 0.4639 |
+| 0.2981        | 17.2414 | 4000 | 0.6604          | 0.4617 |
+| 0.26          | 19.3966 | 4500 | 0.6835          | 0.4538 |
+| 0.2247        | 21.5517 | 5000 | 0.6830          | 0.4304 |
+| 0.1959        | 23.7069 | 5500 | 0.6905          | 0.4285 |
+| 0.1769        | 25.8621 | 6000 | 0.7278          | 0.4254 |
+| 0.1483        | 28.0172 | 6500 | 0.7290          | 0.4124 |
+
 
 ### Framework versions
 

config.json

@@ -78,7 +78,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 0,
+  "pad_token_id": 29,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b9622004bcc77284293db2258baf829183a4d3cfd02f7b331527254ed60c226
+oid sha256:de399986abca785545b05f5b0935f4f9358c5e95714575063e1225a83bbb6750
 size 1261938680

runs/May11_18-12-44_30c0cb923c2a/events.out.tfevents.1715451223.30c0cb923c2a.236.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf231764071e2b5d3ec27d67e94d7b70b4552e6a7f53c8c6a7d0fdb63792c98
+size 13391

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95fb0f06e9f11946e25b04a5da24d7ced6070b2bce513d1e7c74ee9f5972830
+oid sha256:63019ea26818b45657c886c12d23f70c0dbf7fb79f5eb96a1e367002c2bac0ec
 size 4984