arslanarjumand/wav2vec-repeat

README.md

@@ -0,0 +1,78 @@
+---
+license: mit
+base_model: arslanarjumand/wav2vec-reptiles
+tags:
+- generated_from_trainer
+model-index:
+- name: wav2vec-repeat
+  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. -->
+
+# wav2vec-repeat
+
+This model is a fine-tuned version of [arslanarjumand/wav2vec-reptiles](https://huggingface.co/arslanarjumand/wav2vec-reptiles) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 205.9549
+- Pcc Accuracy: 0.8004
+- Pcc Fluency: 0.7759
+- Pcc Total Score: 0.8207
+- Pcc Content: 0.7220
+
+## 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: 2.5e-05
+- train_batch_size: 4
+- eval_batch_size: 6
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.5
+- num_epochs: 50
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Pcc Accuracy | Pcc Fluency | Pcc Total Score | Pcc Content |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:-----------:|:---------------:|:-----------:|
+| 507.295       | 3.54  | 500  | 538.7184        | 0.2592       | 0.2368      | 0.2807          | 0.3206      |
+| 267.4833      | 7.08  | 1000 | 374.0983        | 0.5787       | 0.5582      | 0.5900          | 0.5040      |
+| 246.7156      | 10.62 | 1500 | 483.3237        | 0.6618       | 0.6387      | 0.6761          | 0.5837      |
+| 269.7238      | 14.16 | 2000 | 446.4642        | 0.6964       | 0.6691      | 0.7131          | 0.6288      |
+| 289.3261      | 17.7  | 2500 | 244.4726        | 0.7201       | 0.6928      | 0.7371          | 0.6482      |
+| 249.89        | 21.24 | 3000 | 413.8036        | 0.7340       | 0.7052      | 0.7548          | 0.6796      |
+| 235.8593      | 24.78 | 3500 | 251.3629        | 0.7472       | 0.7217      | 0.7676          | 0.6808      |
+| 217.7143      | 28.32 | 4000 | 212.4162        | 0.7779       | 0.7547      | 0.7973          | 0.6948      |
+| 123.7326      | 31.86 | 4500 | 362.4697        | 0.7782       | 0.7528      | 0.7987          | 0.7062      |
+| 132.7905      | 35.4  | 5000 | 228.9714        | 0.7826       | 0.7603      | 0.8021          | 0.6987      |
+| 111.7989      | 38.94 | 5500 | 189.2367        | 0.7985       | 0.7754      | 0.8188          | 0.7169      |
+| 104.5979      | 42.48 | 6000 | 271.8181        | 0.7929       | 0.7692      | 0.8143          | 0.7192      |
+| 115.256       | 46.02 | 6500 | 220.4324        | 0.8008       | 0.7753      | 0.8209          | 0.7230      |
+| 86.3804       | 49.56 | 7000 | 205.9549        | 0.8004       | 0.7759      | 0.8207          | 0.7220      |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.2
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,94 @@
+{
+  "_name_or_path": "arslanarjumand/wav2vec-reptiles",
+  "activation_dropout": 0.019,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForSequenceClassification"
+  ],
+  "attention_dropout": 0.0094,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.005,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.008,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0005,
+  "left_max_position_embeddings": 64,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 2,
+  "mask_feature_prob": 0.0575,
+  "mask_time_length": 3,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.0885,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "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": "4.38.1",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": null,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c94f872b67ebfbb90775d2d156a52a21c357c4bb8a24d52396955fa2cde4d7
+size 1164530912

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c87c43e8936bd9ff7c194c01942cf5e0de67757642f189982ee5840c43433c
+size 4920