End of training

README.md

@@ -0,0 +1,96 @@
+---
+license: apache-2.0
+base_model: facebook/hubert-base-ls960
+tags:
+- generated_from_trainer
+datasets:
+- speech_commands
+metrics:
+- accuracy
+model-index:
+- name: hubert-base-ls960-speech-commands
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: speech_commands
+      type: speech_commands
+      config: v0.02
+      split: None
+      args: v0.02
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.8057553956834532
+---
+
+<!-- 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. -->
+
+# hubert-base-ls960-speech-commands
+
+This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on the speech_commands dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0829
+- Accuracy: 0.8058
+
+## 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: 48
+- eval_batch_size: 48
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 1.8285        | 1.0   | 824   | 1.9509          | 0.7167   |
+| 0.5292        | 2.0   | 1648  | 1.3813          | 0.7909   |
+| 0.3554        | 3.0   | 2472  | 1.1773          | 0.7941   |
+| 0.2873        | 4.0   | 3296  | 1.2437          | 0.7981   |
+| 0.2525        | 5.0   | 4120  | 1.2514          | 0.8004   |
+| 0.2941        | 6.0   | 4944  | 1.2243          | 0.7995   |
+| 0.1809        | 7.0   | 5768  | 1.1965          | 0.8008   |
+| 0.2313        | 8.0   | 6592  | 1.0694          | 0.8022   |
+| 0.1917        | 9.0   | 7416  | 1.0618          | 0.7995   |
+| 0.1212        | 10.0  | 8240  | 1.0972          | 0.8026   |
+| 0.185         | 11.0  | 9064  | 1.0868          | 0.8017   |
+| 0.143         | 12.0  | 9888  | 1.1558          | 0.8031   |
+| 0.2227        | 13.0  | 10712 | 1.0550          | 0.8040   |
+| 0.1884        | 14.0  | 11536 | 1.0384          | 0.8022   |
+| 0.1183        | 15.0  | 12360 | 1.0169          | 0.8035   |
+| 0.1849        | 16.0  | 13184 | 1.0061          | 0.8035   |
+| 0.141         | 17.0  | 14008 | 1.0337          | 0.8053   |
+| 0.1328        | 18.0  | 14832 | 1.0829          | 0.8058   |
+| 0.1238        | 19.0  | 15656 | 1.0576          | 0.8053   |
+| 0.0932        | 20.0  | 16480 | 1.0641          | 0.8053   |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,152 @@
+{
+  "_name_or_path": "facebook/hubert-base-ls960",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "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,
+  "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_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 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": 0.1,
+  "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": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e23706f3a820cb4ed25d98a9e0cb2ea2032dfea0f63b20722f69038ec53efb92
+size 378336904

preprocessor_config.json

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

runs/Oct01_09-39-27_ki-g0010/events.out.tfevents.1727775572.ki-g0010.1555826.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d0282c5e7ae248a4ea355f7c3776cc16eef4295e7beb4d8c21740a413db90ab
+size 13880

runs/Oct01_09-41-54_ki-g0010/events.out.tfevents.1727775719.ki-g0010.1558223.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98ac2fe1d84a6d29b21d1f0f308f6a4f9c22849e0fb92f1261f91b08b8db9ff
+size 709490

runs/Oct01_09-41-54_ki-g0010/events.out.tfevents.1727776568.ki-g0010.1558223.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23ccf8e62d3c3f242753631b01ba3cb1f2610879c81d0236d5929181718d2891
+size 417

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7a797b97bc4aa390371970b1809629e0ee56acbe55467eb33f8259bb6c9eff
+size 5240