End of training

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: results
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# results
+
+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:
+- Loss: 1.9132
+- Accuracy: 0.6351
+- F1: 0.6301
+- Precision: 0.6315
+- Recall: 0.6351
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- 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
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.586         | 1.0   | 855   | 0.6272          | 0.6316   | 0.5289 | 0.5719    | 0.6316 |
+| 0.6905        | 2.0   | 1710  | 0.5821          | 0.6520   | 0.5420 | 0.4804    | 0.6520 |
+| 0.5642        | 3.0   | 2565  | 0.6012          | 0.6497   | 0.5396 | 0.4769    | 0.6497 |
+| 0.6263        | 4.0   | 3420  | 0.6040          | 0.6526   | 0.5903 | 0.6403    | 0.6526 |
+| 0.7556        | 5.0   | 4275  | 0.6088          | 0.6485   | 0.5406 | 0.4838    | 0.6485 |
+| 0.4614        | 6.0   | 5130  | 0.6061          | 0.6614   | 0.6348 | 0.6523    | 0.6614 |
+| 0.4232        | 7.0   | 5985  | 0.6184          | 0.6456   | 0.6401 | 0.6355    | 0.6456 |
+| 0.519         | 8.0   | 6840  | 0.6186          | 0.6538   | 0.5449 | 0.4874    | 0.6538 |
+| 0.4847        | 9.0   | 7695  | 0.6226          | 0.6421   | 0.5652 | 0.5948    | 0.6421 |
+| 0.5505        | 10.0  | 8550  | 0.6857          | 0.6363   | 0.5903 | 0.6241    | 0.6363 |
+| 0.5499        | 11.0  | 9405  | 0.6684          | 0.6491   | 0.6462 | 0.6470    | 0.6491 |
+| 0.2869        | 12.0  | 10260 | 0.7500          | 0.6468   | 0.6341 | 0.6389    | 0.6468 |
+| 0.2607        | 13.0  | 11115 | 0.9291          | 0.6351   | 0.6354 | 0.6357    | 0.6351 |
+| 0.3495        | 14.0  | 11970 | 1.1298          | 0.6444   | 0.6415 | 0.6396    | 0.6444 |
+| 0.2483        | 15.0  | 12825 | 1.3714          | 0.6246   | 0.6181 | 0.6320    | 0.6246 |
+| 0.3764        | 16.0  | 13680 | 1.4325          | 0.6515   | 0.6454 | 0.6475    | 0.6515 |
+| 0.373         | 17.0  | 14535 | 1.6233          | 0.6491   | 0.6473 | 0.6457    | 0.6491 |
+| 0.0677        | 18.0  | 15390 | 1.7408          | 0.6450   | 0.6434 | 0.6429    | 0.6450 |
+| 0.0665        | 19.0  | 16245 | 1.8868          | 0.6351   | 0.6296 | 0.6316    | 0.6351 |
+| 0.0044        | 20.0  | 17100 | 1.9132          | 0.6351   | 0.6301 | 0.6315    | 0.6351 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,128 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498f86f00d8f51721c43062fc37de88603fcdda37c5a690df518ffe4d6f4c162
+size 378303396

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ebb5c074c4e876e9fc8efe315a3c92065e285f90c78f90ff52120898cba067
+size 5048