Upload folder using huggingface_hub

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: openai/whisper-small
+tags:
+- audio-classification
+- generated_from_trainer
+datasets:
+- superb
+metrics:
+- accuracy
+model-index:
+- name: superb_ks_42
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: superb
+      type: superb
+      config: ks
+      split: validation
+      args: ks
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9848484848484849
+---
+
+<!-- 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. -->
+
+# superb_ks_42
+
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the superb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0976
+- Accuracy: 0.9848
+
+## 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: 4
+- 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.3599        | 1.0   | 1597  | 0.1546          | 0.9707   |
+| 0.0819        | 2.0   | 3194  | 0.0998          | 0.9762   |
+| 0.0635        | 3.0   | 4791  | 0.1049          | 0.9800   |
+| 0.0437        | 4.0   | 6388  | 0.0905          | 0.9797   |
+| 0.0411        | 5.0   | 7985  | 0.0898          | 0.9809   |
+| 0.0283        | 6.0   | 9582  | 0.1006          | 0.9812   |
+| 0.0229        | 7.0   | 11179 | 0.0976          | 0.9848   |
+| 0.0186        | 8.0   | 12776 | 0.1143          | 0.9825   |
+| 0.0094        | 9.0   | 14373 | 0.1136          | 0.9835   |
+| 0.0066        | 10.0  | 15970 | 0.1172          | 0.9834   |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9848484848484849,
+    "eval_loss": 0.09762121737003326,
+    "eval_runtime": 138.169,
+    "eval_samples_per_second": 49.201,
+    "eval_steps_per_second": 0.195,
+    "test_accuracy": 0.9383317104836092,
+    "test_loss": 0.5075491666793823,
+    "test_runtime": 68.0743,
+    "test_samples_per_second": 45.259,
+    "test_steps_per_second": 0.191,
+    "total_flos": 6.415922957241599e+19,
+    "train_accuracy": 0.9941676126355345,
+    "train_loss": 0.028768757358193398,
+    "train_runtime": 921.5231,
+    "train_samples_per_second": 55.445,
+    "train_steps_per_second": 13.862
+}

config.json

@@ -0,0 +1,181 @@
+{
+  "_name_or_path": "openai/whisper-small",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForAudioClassification"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50257,
+  "finetuning_task": "audio-classification",
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
+  "id2label": {
+    "0": "yes",
+    "1": "no",
+    "10": "_silence_",
+    "11": "_unknown_",
+    "2": "up",
+    "3": "down",
+    "4": "left",
+    "5": "right",
+    "6": "on",
+    "7": "off",
+    "8": "stop",
+    "9": "go"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "_silence_": "10",
+    "_unknown_": "11",
+    "down": "3",
+    "go": "9",
+    "left": "4",
+    "no": "1",
+    "off": "7",
+    "on": "6",
+    "right": "5",
+    "stop": "8",
+    "up": "2",
+    "yes": "0"
+  },
+  "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,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 12,
+  "num_mel_bins": 80,
+  "pad_token_id": 50257,
+  "scale_embedding": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50360,
+    50361,
+    50362
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51865
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9848484848484849,
+    "eval_loss": 0.09762121737003326,
+    "eval_runtime": 138.169,
+    "eval_samples_per_second": 49.201,
+    "eval_steps_per_second": 0.195
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb1b8c84b7e2ffd638317a96698440612045be22bd2e7663a3c2453125d4924
+size 353436648

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83155745ad5509e3078c211305b8f9c9f6af7158260174b6bd4526a2e5dcf6b7
+size 326432

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8818682aa32ec15f5f35e7d4adf2fb779a1e979aab03da0500138a0969c13052
+size 148016

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e92a7e03681287a1f2c593946bc21cd5c0e5fbed9d35d517884024b6c3c511
+size 2452640

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

test_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "test_accuracy": 0.9383317104836092,
+    "test_loss": 0.5075491666793823,
+    "test_runtime": 68.0743,
+    "test_samples_per_second": 45.259,
+    "test_steps_per_second": 0.191
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_accuracy": 0.9941676126355345,
+    "train_loss": 0.028768757358193398,
+    "train_runtime": 921.5231,
+    "train_samples_per_second": 55.445,
+    "train_steps_per_second": 13.862
+}

trainer_state.json

@@ -0,0 +1,225 @@
+{
+  "best_metric": 0.9848484848484849,
+  "best_model_checkpoint": "audio/train/checkpoint/whisper-small/superb_ks_42/checkpoint-11179",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 15970,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6261740763932373,
+      "grad_norm": 8.361194610595703,
+      "learning_rate": 3.1308703819661866e-05,
+      "loss": 0.3599,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9707266843189173,
+      "eval_loss": 0.15458986163139343,
+      "eval_runtime": 143.1918,
+      "eval_samples_per_second": 47.475,
+      "eval_steps_per_second": 0.189,
+      "step": 1597
+    },
+    {
+      "epoch": 1.2523481527864746,
+      "grad_norm": 0.06838619709014893,
+      "learning_rate": 4.859806581785292e-05,
+      "loss": 0.0958,
+      "step": 2000
+    },
+    {
+      "epoch": 1.878522229179712,
+      "grad_norm": 6.442350387573242,
+      "learning_rate": 4.51193209490016e-05,
+      "loss": 0.0819,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9761694616063548,
+      "eval_loss": 0.09978443384170532,
+      "eval_runtime": 138.5727,
+      "eval_samples_per_second": 49.057,
+      "eval_steps_per_second": 0.195,
+      "step": 3194
+    },
+    {
+      "epoch": 2.504696305572949,
+      "grad_norm": 0.008366833440959454,
+      "learning_rate": 4.1640576080150286e-05,
+      "loss": 0.0635,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.979994115916446,
+      "eval_loss": 0.10489170253276825,
+      "eval_runtime": 138.2853,
+      "eval_samples_per_second": 49.159,
+      "eval_steps_per_second": 0.195,
+      "step": 4791
+    },
+    {
+      "epoch": 3.1308703819661865,
+      "grad_norm": 0.06020672991871834,
+      "learning_rate": 3.8161831211298965e-05,
+      "loss": 0.0569,
+      "step": 5000
+    },
+    {
+      "epoch": 3.757044458359424,
+      "grad_norm": 0.005801007151603699,
+      "learning_rate": 3.468308634244764e-05,
+      "loss": 0.0437,
+      "step": 6000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9796999117387467,
+      "eval_loss": 0.0905165895819664,
+      "eval_runtime": 138.7617,
+      "eval_samples_per_second": 48.99,
+      "eval_steps_per_second": 0.195,
+      "step": 6388
+    },
+    {
+      "epoch": 4.383218534752661,
+      "grad_norm": 1.9717774391174316,
+      "learning_rate": 3.120434147359633e-05,
+      "loss": 0.0411,
+      "step": 7000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.980876728449544,
+      "eval_loss": 0.08979170769453049,
+      "eval_runtime": 138.2656,
+      "eval_samples_per_second": 49.166,
+      "eval_steps_per_second": 0.195,
+      "step": 7985
+    },
+    {
+      "epoch": 5.009392611145898,
+      "grad_norm": 0.09022530913352966,
+      "learning_rate": 2.7725596604745007e-05,
+      "loss": 0.0386,
+      "step": 8000
+    },
+    {
+      "epoch": 5.635566687539136,
+      "grad_norm": 0.003507192712277174,
+      "learning_rate": 2.4246851735893692e-05,
+      "loss": 0.0283,
+      "step": 9000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9811709326272433,
+      "eval_loss": 0.10055801272392273,
+      "eval_runtime": 139.0437,
+      "eval_samples_per_second": 48.891,
+      "eval_steps_per_second": 0.194,
+      "step": 9582
+    },
+    {
+      "epoch": 6.261740763932373,
+      "grad_norm": 0.6481895446777344,
+      "learning_rate": 2.076810686704237e-05,
+      "loss": 0.0322,
+      "step": 10000
+    },
+    {
+      "epoch": 6.88791484032561,
+      "grad_norm": 15.71690559387207,
+      "learning_rate": 1.7289361998191053e-05,
+      "loss": 0.0229,
+      "step": 11000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9848484848484849,
+      "eval_loss": 0.09762121737003326,
+      "eval_runtime": 138.2722,
+      "eval_samples_per_second": 49.164,
+      "eval_steps_per_second": 0.195,
+      "step": 11179
+    },
+    {
+      "epoch": 7.514088916718848,
+      "grad_norm": 0.0020187441259622574,
+      "learning_rate": 1.3810617129339735e-05,
+      "loss": 0.0186,
+      "step": 12000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9824948514268903,
+      "eval_loss": 0.11428509652614594,
+      "eval_runtime": 139.2486,
+      "eval_samples_per_second": 48.819,
+      "eval_steps_per_second": 0.194,
+      "step": 12776
+    },
+    {
+      "epoch": 8.140262993112085,
+      "grad_norm": 0.6445852518081665,
+      "learning_rate": 1.0331872260488417e-05,
+      "loss": 0.0159,
+      "step": 13000
+    },
+    {
+      "epoch": 8.766437069505322,
+      "grad_norm": 0.003636428155004978,
+      "learning_rate": 6.853127391637097e-06,
+      "loss": 0.0094,
+      "step": 14000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9835245660488379,
+      "eval_loss": 0.11361410468816757,
+      "eval_runtime": 139.9155,
+      "eval_samples_per_second": 48.586,
+      "eval_steps_per_second": 0.193,
+      "step": 14373
+    },
+    {
+      "epoch": 9.39261114589856,
+      "grad_norm": 0.0017493839841336012,
+      "learning_rate": 3.3743825227857787e-06,
+      "loss": 0.0066,
+      "step": 15000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9833774639599883,
+      "eval_loss": 0.11724763363599777,
+      "eval_runtime": 138.7939,
+      "eval_samples_per_second": 48.979,
+      "eval_steps_per_second": 0.195,
+      "step": 15970
+    },
+    {
+      "epoch": 10.0,
+      "step": 15970,
+      "total_flos": 6.415922957241599e+19,
+      "train_loss": 0.057567716346506634,
+      "train_runtime": 27132.3161,
+      "train_samples_per_second": 18.831,
+      "train_steps_per_second": 0.589
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 15970,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 6.415922957241599e+19,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f07a729079763eab0fd2151437a9f3c4e6fbf2c0bee81734b59d0d4c00efba
+size 5112