Model save

README.md

@@ -0,0 +1,90 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base-960h
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: Helldivers2ASR_V2
+  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. -->
+
+# Helldivers2ASR_V2
+
+This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 600.7576
+- Wer: 0.1781
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 1606.3359     | 1.0   | 220  | 1090.8248       | 0.5061 |
+| 1121.8479     | 2.0   | 440  | 865.5970        | 0.4061 |
+| 946.2823      | 3.0   | 660  | 820.0260        | 0.3625 |
+| 783.6905      | 4.0   | 880  | 707.9121        | 0.3211 |
+| 695.3827      | 5.0   | 1100 | 838.1756        | 0.3111 |
+| 622.7798      | 6.0   | 1320 | 742.3585        | 0.2847 |
+| 553.7608      | 7.0   | 1540 | 716.7022        | 0.2676 |
+| 491.1993      | 8.0   | 1760 | 761.7335        | 0.2603 |
+| 473.3195      | 9.0   | 1980 | 567.7379        | 0.2178 |
+| 437.2569      | 10.0  | 2200 | 702.8529        | 0.2387 |
+| 399.1445      | 11.0  | 2420 | 606.8059        | 0.2159 |
+| 365.5832      | 12.0  | 2640 | 668.2637        | 0.2218 |
+| 352.0708      | 13.0  | 2860 | 618.1540        | 0.2013 |
+| 345.8254      | 14.0  | 3080 | 605.1513        | 0.2025 |
+| 301.8691      | 15.0  | 3300 | 534.0126        | 0.1824 |
+| 306.2117      | 16.0  | 3520 | 525.6846        | 0.1769 |
+| 276.5106      | 17.0  | 3740 | 588.5739        | 0.1812 |
+| 278.9943      | 18.0  | 3960 | 586.8976        | 0.1856 |
+| 254.1533      | 19.0  | 4180 | 565.0082        | 0.1785 |
+| 264.3702      | 20.0  | 4400 | 636.0349        | 0.1922 |
+| 246.2727      | 21.0  | 4620 | 574.8817        | 0.1783 |
+| 237.4068      | 22.0  | 4840 | 525.9941        | 0.1700 |
+| 229.2964      | 23.0  | 5060 | 583.3613        | 0.1751 |
+| 228.483       | 24.0  | 5280 | 625.8549        | 0.1804 |
+| 225.443       | 25.0  | 5500 | 592.6890        | 0.1779 |
+| 223.0987      | 26.0  | 5720 | 610.0046        | 0.1781 |
+| 211.6382      | 27.0  | 5940 | 600.6169        | 0.1783 |
+| 215.4619      | 28.0  | 6160 | 598.9771        | 0.1787 |
+| 220.9056      | 29.0  | 6380 | 600.8087        | 0.1783 |
+| 222.1433      | 30.0  | 6600 | 600.7576        | 0.1781 |
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.5.1+cu121
+- Datasets 3.6.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base-960h",
+  "activation_dropout": 0.1,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "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_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.05,
+  "model_type": "wav2vec2",
+  "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": "4.44.0",
+  "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:fe6446293ae0a7864146c962bd7a254f44c6cd554d7d8ed1187db4e4cecb7df5
+size 377611120

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "do_normalize": true,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "return_attention_mask": false,
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a5ac5f909ac46ee0cff8e56b7936b98549642616256a1eb1094ac9e1361878
+size 5240

vocab.json

@@ -0,0 +1,34 @@
+{
+  "'": 27,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "A": 7,
+  "B": 24,
+  "C": 19,
+  "D": 14,
+  "E": 5,
+  "F": 20,
+  "G": 21,
+  "H": 11,
+  "I": 10,
+  "J": 29,
+  "K": 26,
+  "L": 15,
+  "M": 17,
+  "N": 9,
+  "O": 8,
+  "P": 23,
+  "Q": 30,
+  "R": 13,
+  "S": 12,
+  "T": 6,
+  "U": 16,
+  "V": 25,
+  "W": 18,
+  "X": 28,
+  "Y": 22,
+  "Z": 31,
+  "|": 4
+}