Model save

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: mouseyy/result_data-1
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_17_0
+model-index:
+- name: result_data_2-1
+  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. -->
+
+# result_data_2-1
+
+This model is a fine-tuned version of [mouseyy/result_data-1](https://huggingface.co/mouseyy/result_data-1) on the common_voice_17_0 dataset.
+
+## 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: 2.1500224030495643e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 282
+- training_steps: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 39,
+  "<s>": 38
+}

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.009099181073703366,
+    "eval_cer": 0.16934373565855898,
+    "eval_loss": 0.22408190369606018,
+    "eval_runtime": 16.3688,
+    "eval_samples": 500,
+    "eval_samples_per_second": 30.546,
+    "eval_steps_per_second": 0.977,
+    "eval_wer": 0.36512878573450325,
+    "total_flos": 7.434959474550374e+16,
+    "train_loss": 0.2877780914306641,
+    "train_runtime": 23.4586,
+    "train_samples": 35144,
+    "train_samples_per_second": 13.641,
+    "train_steps_per_second": 0.426
+}

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "mouseyy/result_data-1",
+  "activation_dropout": 0.045364883442839066,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.015685335465631136,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "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": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.01959937819386322,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.02424542658251297,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.045364883442839066,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.052363375051395544,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.052363375051395544,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 37,
+  "proj_codevector_dim": 768,
+  "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": "4.49.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 40,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.009099181073703366,
+    "eval_cer": 0.16934373565855898,
+    "eval_loss": 0.22408190369606018,
+    "eval_runtime": 16.3688,
+    "eval_samples": 500,
+    "eval_samples_per_second": 30.546,
+    "eval_steps_per_second": 0.977,
+    "eval_wer": 0.36512878573450325
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa968081d9e5e259364b1a84ccb89e38d740eb4bd43754244cb61254ac1a11d9
+size 1261971480

preprocessor_config.json

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

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "36": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.009099181073703366,
+    "total_flos": 7.434959474550374e+16,
+    "train_loss": 0.2877780914306641,
+    "train_runtime": 23.4586,
+    "train_samples": 35144,
+    "train_samples_per_second": 13.641,
+    "train_steps_per_second": 0.426
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.009099181073703366,
+  "eval_steps": 1000.0,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009099181073703366,
+      "step": 10,
+      "total_flos": 7.434959474550374e+16,
+      "train_loss": 0.2877780914306641,
+      "train_runtime": 23.4586,
+      "train_samples_per_second": 13.641,
+      "train_steps_per_second": 0.426
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.434959474550374e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae7d0665721245cb59f0e25b99b6644cd7a071db946c39a655ff2dca26b5242
+size 5432

vocab.json

@@ -0,0 +1,40 @@
+{
+  "+": 18,
+  "[PAD]": 37,
+  "[UNK]": 36,
+  "|": 34,
+  "а": 31,
+  "б": 29,
+  "в": 33,
+  "г": 6,
+  "д": 27,
+  "е": 10,
+  "ж": 5,
+  "з": 21,
+  "и": 35,
+  "й": 25,
+  "к": 30,
+  "л": 12,
+  "м": 3,
+  "н": 0,
+  "о": 9,
+  "п": 28,
+  "р": 14,
+  "с": 20,
+  "т": 11,
+  "у": 19,
+  "ф": 4,
+  "х": 2,
+  "ц": 17,
+  "ч": 7,
+  "ш": 13,
+  "щ": 26,
+  "ь": 24,
+  "ю": 22,
+  "я": 15,
+  "є": 8,
+  "і": 32,
+  "ї": 16,
+  "ґ": 23,
+  "’": 1
+}