End of training

README.md

@@ -1,8 +1,8 @@
 ---
 license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
 tags:
 - generated_from_trainer
-base_model: paruwka/wav2vec2-base-timit-demo-google-colab
 metrics:
 - wer
 model-index:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # wav2vec2-base-timit-demo-google-colab
 
-This model is a fine-tuned version of [paruwka/wav2vec2-base-timit-demo-google-colab](https://huggingface.co/paruwka/wav2vec2-base-timit-demo-google-colab) on the None dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0015
-- Wer: 0.5828
+- Loss: 0.6025
+- Wer: 0.4421
 
 ## Model description
 
@@ -37,31 +37,29 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 4
+- learning_rate: 0.0001
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 50
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 30
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.4127        | 4.46  | 500  | 0.8997          | 0.6221 |
-| 0.38          | 8.93  | 1000 | 0.9162          | 0.6091 |
-| 0.3382        | 13.39 | 1500 | 0.9044          | 0.6011 |
-| 0.3074        | 17.86 | 2000 | 0.9529          | 0.6030 |
-| 0.274         | 22.32 | 2500 | 0.9327          | 0.5919 |
-| 0.2558        | 26.79 | 3000 | 0.9906          | 0.5895 |
-| 0.2462        | 31.25 | 3500 | 0.9873          | 0.5854 |
-| 0.2215        | 35.71 | 4000 | 1.0059          | 0.5839 |
-| 0.2313        | 40.18 | 4500 | 1.0142          | 0.5823 |
-| 0.2182        | 44.64 | 5000 | 0.9998          | 0.5804 |
-| 0.2123        | 49.11 | 5500 | 1.0015          | 0.5828 |
+| 2.8753        | 3.05  | 500  | 2.1566          | 0.9599 |
+| 1.3505        | 6.1   | 1000 | 0.7121          | 0.6287 |
+| 0.7278        | 9.15  | 1500 | 0.5651          | 0.5202 |
+| 0.5178        | 12.2  | 2000 | 0.5785          | 0.4942 |
+| 0.3887        | 15.24 | 2500 | 0.5684          | 0.4723 |
+| 0.3194        | 18.29 | 3000 | 0.5718          | 0.4635 |
+| 0.2873        | 21.34 | 3500 | 0.5871          | 0.4552 |
+| 0.24          | 24.39 | 4000 | 0.6020          | 0.4501 |
+| 0.2151        | 27.44 | 4500 | 0.6025          | 0.4421 |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "paruwka/wav2vec2-base-timit-demo-google-colab",
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
   "activation_dropout": 0.0,
   "adapter_attn_dim": null,
   "adapter_kernel_size": 3,
@@ -86,7 +86,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 64,
+  "pad_token_id": 67,
   "proj_codevector_dim": 768,
   "tdnn_dilation": [
     1,
@@ -112,6 +112,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
   "use_weighted_layer_sum": false,
-  "vocab_size": 65,
+  "vocab_size": 68,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c57b40a49657db7423cca0768535f00e5c70164d2ae0a6b5eb9f0003e2be70
-size 1262073980
+oid sha256:29e41458e246dd613f256b1b77751da977fa742c5eb81ba3f3e69293d3c0df99
+size 1262086280

runs/May26_13-53-18_483ac4db5d6b/events.out.tfevents.1716731677.483ac4db5d6b.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec032371ad7a27ecf2d98d525d644634b9421911098422a13435dd3ac2a5bfc5
+size 6541

runs/May26_13-53-18_483ac4db5d6b/events.out.tfevents.1716732742.483ac4db5d6b.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c451d3280a078351123809da455661b62145ea75e38f65eaeba6012b56be08
+size 6678

runs/May26_13-53-18_483ac4db5d6b/events.out.tfevents.1716732890.483ac4db5d6b.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d214691325931f31a0dbd33d459d743cc2ea982ca0721d3b0f6c111a0368f915
+size 18236

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640119fe9ad7b83ca8c9edcd0742999a1f0971d383a00f6ed87c02dc0cc192c4
+oid sha256:8e30ee8ec81a13b3f7437b0f5c02c638ab7efe9278c91a9d0f596f447ab46e85
 size 4920