End of training

README.md

@@ -1,10 +1,10 @@
 ---
-base_model: Thienpkae/wav2vec2-large-xls-r-vi-colab
 license: apache-2.0
-metrics:
-- wer
+base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
+metrics:
+- wer
 model-index:
 - name: wav2vec2-large-xls-r-vi-colab
   results: []
@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-large-xls-r-vi-colab
 
-This model is a fine-tuned version of [Thienpkae/wav2vec2-large-xls-r-vi-colab](https://huggingface.co/Thienpkae/wav2vec2-large-xls-r-vi-colab) on an unknown dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8989
-- Wer: 0.9376
-- Cer: 0.3861
+- Loss: 4.5540
+- Wer: 1.0
+- Cer: 1.0
 
 ## Model description
 
@@ -44,18 +44,26 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 330
+- lr_scheduler_warmup_steps: 500
 - num_epochs: 30
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
-| 3.533         | 7.5   | 165  | 3.3635          | 1.0    | 1.0    |
-| 3.5135        | 15.0  | 330  | 3.3336          | 1.0    | 1.0    |
-| 3.6414        | 22.5  | 495  | 3.0578          | 0.9995 | 0.8722 |
-| 2.1098        | 30.0  | 660  | 1.8989          | 0.9376 | 0.3861 |
+| Training Loss | Epoch   | Step | Validation Loss | Wer | Cer |
+|:-------------:|:-------:|:----:|:---------------:|:---:|:---:|
+| 9.6481        | 2.3864  | 315  | 4.4676          | 1.0 | 1.0 |
+| 3.8703        | 4.7727  | 630  | 4.4033          | 1.0 | 1.0 |
+| 3.4149        | 7.1591  | 945  | 4.7546          | 1.0 | 1.0 |
+| 3.4323        | 9.5455  | 1260 | 4.2532          | 1.0 | 1.0 |
+| 3.4127        | 11.9318 | 1575 | 4.6692          | 1.0 | 1.0 |
+| 3.4185        | 14.3182 | 1890 | 4.3411          | 1.0 | 1.0 |
+| 3.4112        | 16.7045 | 2205 | 4.5614          | 1.0 | 1.0 |
+| 3.4074        | 19.0909 | 2520 | 4.3545          | 1.0 | 1.0 |
+| 3.4073        | 21.4773 | 2835 | 4.4929          | 1.0 | 1.0 |
+| 3.4004        | 23.8636 | 3150 | 4.6089          | 1.0 | 1.0 |
+| 3.4099        | 26.25   | 3465 | 4.5189          | 1.0 | 1.0 |
+| 3.3972        | 28.6364 | 3780 | 4.5540          | 1.0 | 1.0 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Thienpkae/wav2vec2-large-xls-r-vi-colab",
+  "_name_or_path": "facebook/wav2vec2-base",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
@@ -87,7 +87,7 @@
   "num_hidden_layers": 12,
   "num_negatives": 100,
   "output_hidden_size": 768,
-  "pad_token_id": 93,
+  "pad_token_id": 92,
   "proj_codevector_dim": 256,
   "tdnn_dilation": [
     1,
@@ -113,6 +113,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "use_weighted_layer_sum": false,
-  "vocab_size": 96,
+  "vocab_size": 95,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1852cda5ba479a97363810a19a078b2b915cbe7c427159e2b83da631e434ce9f
-size 377807992
+oid sha256:a989d17eaeaf2ffd399f853c680ae8d26f52e45bb0a0d50e97feec5a04b21576
+size 377804916

runs/Jun30_12-30-38_d104d5d394a4/events.out.tfevents.1719750711.d104d5d394a4.945.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45f8566aafb0ddb738e07260a5c27f3228420d00f33207ac596c9eba6b9367f5
+size 13814

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bbb4c33245ac2ddda00f5a988bf816feb4ce96aa0a1c3bd1818957816c58043
+oid sha256:16eb319d9dacd339990dc6b25e8c325031ef603f003ee8b8f4e2d55bb83f3f2f
 size 5112