End of training

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-base
+tags:
+- generated_from_trainer
+datasets:
+- speech_commands
+metrics:
+- accuracy
+model-index:
+- name: wav2vec2-base-finetuned-ks
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: speech_commands
+      type: speech_commands
+      config: v0.02
+      split: validation
+      args: v0.02
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9632338208775797
+---
+
+<!-- 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. -->
+
+# wav2vec2-base-finetuned-ks
+
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the speech_commands dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5562
+- Accuracy: 0.9632
+
+## 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: 3e-05
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 1024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.5366        | 1.0   | 83   | 2.2424          | 0.8575   |
+| 1.963         | 2.0   | 166  | 1.6987          | 0.9537   |
+| 1.7887        | 3.0   | 249  | 1.5562          | 0.9632   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,194 @@
+{
+  "_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": "yes",
+    "1": "no",
+    "10": "zero",
+    "11": "one",
+    "12": "two",
+    "13": "three",
+    "14": "four",
+    "15": "five",
+    "16": "six",
+    "17": "seven",
+    "18": "eight",
+    "19": "nine",
+    "2": "up",
+    "20": "bed",
+    "21": "bird",
+    "22": "cat",
+    "23": "dog",
+    "24": "happy",
+    "25": "house",
+    "26": "marvin",
+    "27": "sheila",
+    "28": "tree",
+    "29": "wow",
+    "3": "down",
+    "30": "backward",
+    "31": "forward",
+    "32": "follow",
+    "33": "learn",
+    "34": "visual",
+    "35": "_silence_",
+    "4": "left",
+    "5": "right",
+    "6": "on",
+    "7": "off",
+    "8": "stop",
+    "9": "go"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "_silence_": "35",
+    "backward": "30",
+    "bed": "20",
+    "bird": "21",
+    "cat": "22",
+    "dog": "23",
+    "down": "3",
+    "eight": "18",
+    "five": "15",
+    "follow": "32",
+    "forward": "31",
+    "four": "14",
+    "go": "9",
+    "happy": "24",
+    "house": "25",
+    "learn": "33",
+    "left": "4",
+    "marvin": "26",
+    "nine": "19",
+    "no": "1",
+    "off": "7",
+    "on": "6",
+    "one": "11",
+    "right": "5",
+    "seven": "17",
+    "sheila": "27",
+    "six": "16",
+    "stop": "8",
+    "three": "13",
+    "tree": "28",
+    "two": "12",
+    "up": "2",
+    "visual": "34",
+    "wow": "29",
+    "yes": "0",
+    "zero": "10"
+  },
+  "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:e1f36380771113c079b9a54993eac6ac2d74ae0d497f8c84d8a17874515cbaae
+size 378337328

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
+}

runs/Jun15_16-54-22_6ae1b88b051f/events.out.tfevents.1718470466.6ae1b88b051f.8869.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db175486ebfa8df95fdb9fc73711190eb7e869f20c809ca761a29537939c03e
+size 8502

runs/Jun15_16-57-58_6ae1b88b051f/events.out.tfevents.1718470679.6ae1b88b051f.9984.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fee9046afcf4ac691a6cdc6bf231875b7e6df57c223c6f0afc743a853f79fcd
+size 8090

runs/Jun15_17-02-01_6ae1b88b051f/events.out.tfevents.1718470922.6ae1b88b051f.11136.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec1b405a389eae7b13c042229ca87bfdc9f4de12f252a65b616822a386b5cfc
+size 14216

runs/Jun15_17-02-01_6ae1b88b051f/events.out.tfevents.1718477782.6ae1b88b051f.11136.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246128c0b2125f9577517f7782f7e715145f9c7bfd19d1138e8f0ac76f0c5152
+size 411

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af2f7f22296c766244898dacf711dd0802e2149c22b3bce9ca36a36ec7ced92
+size 5112