Upload folder using huggingface_hub

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: openai/whisper-base
+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: 0.9833774639599883
+---
+
+<!-- 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-base](https://huggingface.co/openai/whisper-base) on the superb dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1152
+- Accuracy: 0.9834
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.6909        | 1.0   | 1597  | 0.1572          | 0.9651   |
+| 0.0891        | 2.0   | 3194  | 0.1597          | 0.9660   |
+| 0.0676        | 3.0   | 4791  | 0.1304          | 0.9719   |
+| 0.0475        | 4.0   | 6388  | 0.0999          | 0.9796   |
+| 0.0433        | 5.0   | 7985  | 0.1079          | 0.9798   |
+| 0.0284        | 6.0   | 9582  | 0.1089          | 0.9803   |
+| 0.0236        | 7.0   | 11179 | 0.1162          | 0.9819   |
+| 0.0193        | 8.0   | 12776 | 0.1152          | 0.9834   |
+| 0.0111        | 9.0   | 14373 | 0.1272          | 0.9821   |
+| 0.0088        | 10.0  | 15970 | 0.1306          | 0.9826   |
+
+
+### 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": 0.9833774639599883,
+    "eval_loss": 0.1151697114109993,
+    "eval_runtime": 46.8398,
+    "eval_samples_per_second": 145.133,
+    "eval_steps_per_second": 0.576,
+    "test_accuracy": 0.9438493995456021,
+    "test_loss": 0.3403080701828003,
+    "test_runtime": 25.5856,
+    "test_samples_per_second": 120.42,
+    "test_steps_per_second": 0.508,
+    "total_flos": 1.46834375382144e+19,
+    "train_accuracy": 0.9970055192390496,
+    "train_loss": 0.010813809931278229,
+    "train_runtime": 278.2509,
+    "train_samples_per_second": 183.626,
+    "train_steps_per_second": 45.908
+}

config.json

@@ -0,0 +1,183 @@
+{
+  "_name_or_path": "openai/whisper-base",
+  "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": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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": 6,
+  "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,
+    50358,
+    50359,
+    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": 0.9833774639599883,
+    "eval_loss": 0.1151697114109993,
+    "eval_runtime": 46.8398,
+    "eval_samples_per_second": 145.133,
+    "eval_steps_per_second": 0.576
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a05dbe0abaf0deb1f6cb6e5376db9d2fcbe3771665d18758aad502a499cac1
+size 82910552

pred_logit_eval.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9c15ac3533841dc2c2b84c6d148b10f4aa39ce476a32d3a87aeeaa25f65a1b
+size 326432

pred_logit_test.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f903091eef439d81c0b923d9c6b58b871d7213b7500677568790e29f430087
+size 148016

pred_logit_train.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126133da9b5d83948ff524916292359869abdd0d4abe7c7f7c467d317eeb9311
+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": 0.9438493995456021,
+    "test_loss": 0.3403080701828003,
+    "test_runtime": 25.5856,
+    "test_samples_per_second": 120.42,
+    "test_steps_per_second": 0.508
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_accuracy": 0.9970055192390496,
+    "train_loss": 0.010813809931278229,
+    "train_runtime": 278.2509,
+    "train_samples_per_second": 183.626,
+    "train_steps_per_second": 45.908
+}

trainer_state.json

@@ -0,0 +1,225 @@
+{
+  "best_metric": 0.9833774639599883,
+  "best_model_checkpoint": "audio/train/checkpoint/whisper-base/superb_ks_42/checkpoint-12776",
+  "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": 47.73924255371094,
+      "learning_rate": 3.1308703819661866e-05,
+      "loss": 0.6909,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9651368049426302,
+      "eval_loss": 0.157243549823761,
+      "eval_runtime": 51.3965,
+      "eval_samples_per_second": 132.266,
+      "eval_steps_per_second": 0.525,
+      "step": 1597
+    },
+    {
+      "epoch": 1.2523481527864746,
+      "grad_norm": 0.04125841706991196,
+      "learning_rate": 4.859806581785292e-05,
+      "loss": 0.1133,
+      "step": 2000
+    },
+    {
+      "epoch": 1.878522229179712,
+      "grad_norm": 0.08289146423339844,
+      "learning_rate": 4.51193209490016e-05,
+      "loss": 0.0891,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9660194174757282,
+      "eval_loss": 0.1596662998199463,
+      "eval_runtime": 48.5884,
+      "eval_samples_per_second": 139.91,
+      "eval_steps_per_second": 0.556,
+      "step": 3194
+    },
+    {
+      "epoch": 2.504696305572949,
+      "grad_norm": 0.05116074159741402,
+      "learning_rate": 4.1640576080150286e-05,
+      "loss": 0.0676,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9719035010297146,
+      "eval_loss": 0.1304367631673813,
+      "eval_runtime": 49.7204,
+      "eval_samples_per_second": 136.724,
+      "eval_steps_per_second": 0.543,
+      "step": 4791
+    },
+    {
+      "epoch": 3.1308703819661865,
+      "grad_norm": 22.351160049438477,
+      "learning_rate": 3.8161831211298965e-05,
+      "loss": 0.0574,
+      "step": 5000
+    },
+    {
+      "epoch": 3.757044458359424,
+      "grad_norm": 2.8176746368408203,
+      "learning_rate": 3.468308634244764e-05,
+      "loss": 0.0475,
+      "step": 6000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.979552809649897,
+      "eval_loss": 0.09990404546260834,
+      "eval_runtime": 49.7998,
+      "eval_samples_per_second": 136.506,
+      "eval_steps_per_second": 0.542,
+      "step": 6388
+    },
+    {
+      "epoch": 4.383218534752661,
+      "grad_norm": 0.7865376472473145,
+      "learning_rate": 3.120434147359633e-05,
+      "loss": 0.0433,
+      "step": 7000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9798470138275963,
+      "eval_loss": 0.10789525508880615,
+      "eval_runtime": 47.3761,
+      "eval_samples_per_second": 143.49,
+      "eval_steps_per_second": 0.57,
+      "step": 7985
+    },
+    {
+      "epoch": 5.009392611145898,
+      "grad_norm": 0.004570442717522383,
+      "learning_rate": 2.7725596604745007e-05,
+      "loss": 0.0392,
+      "step": 8000
+    },
+    {
+      "epoch": 5.635566687539136,
+      "grad_norm": 0.0032151760533452034,
+      "learning_rate": 2.4246851735893692e-05,
+      "loss": 0.0284,
+      "step": 9000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9802883200941453,
+      "eval_loss": 0.10893493890762329,
+      "eval_runtime": 46.9434,
+      "eval_samples_per_second": 144.813,
+      "eval_steps_per_second": 0.575,
+      "step": 9582
+    },
+    {
+      "epoch": 6.261740763932373,
+      "grad_norm": 0.23338378965854645,
+      "learning_rate": 2.076810686704237e-05,
+      "loss": 0.0319,
+      "step": 10000
+    },
+    {
+      "epoch": 6.88791484032561,
+      "grad_norm": 0.0019194560591131449,
+      "learning_rate": 1.7289361998191053e-05,
+      "loss": 0.0236,
+      "step": 11000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9819064430714917,
+      "eval_loss": 0.11618690937757492,
+      "eval_runtime": 47.0803,
+      "eval_samples_per_second": 144.391,
+      "eval_steps_per_second": 0.573,
+      "step": 11179
+    },
+    {
+      "epoch": 7.514088916718848,
+      "grad_norm": 0.0018724563997238874,
+      "learning_rate": 1.3810617129339735e-05,
+      "loss": 0.0193,
+      "step": 12000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9833774639599883,
+      "eval_loss": 0.1151697114109993,
+      "eval_runtime": 47.0809,
+      "eval_samples_per_second": 144.39,
+      "eval_steps_per_second": 0.573,
+      "step": 12776
+    },
+    {
+      "epoch": 8.140262993112085,
+      "grad_norm": 0.00741382222622633,
+      "learning_rate": 1.0331872260488417e-05,
+      "loss": 0.0162,
+      "step": 13000
+    },
+    {
+      "epoch": 8.766437069505322,
+      "grad_norm": 0.004007210489362478,
+      "learning_rate": 6.853127391637097e-06,
+      "loss": 0.0111,
+      "step": 14000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9820535451603413,
+      "eval_loss": 0.12724293768405914,
+      "eval_runtime": 46.9104,
+      "eval_samples_per_second": 144.915,
+      "eval_steps_per_second": 0.576,
+      "step": 14373
+    },
+    {
+      "epoch": 9.39261114589856,
+      "grad_norm": 0.0008135234820656478,
+      "learning_rate": 3.3743825227857787e-06,
+      "loss": 0.0088,
+      "step": 15000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9826419535157399,
+      "eval_loss": 0.13061200082302094,
+      "eval_runtime": 46.6644,
+      "eval_samples_per_second": 145.678,
+      "eval_steps_per_second": 0.579,
+      "step": 15970
+    },
+    {
+      "epoch": 10.0,
+      "step": 15970,
+      "total_flos": 1.46834375382144e+19,
+      "train_loss": 0.08098915571261736,
+      "train_runtime": 8039.2826,
+      "train_samples_per_second": 63.555,
+      "train_steps_per_second": 1.986
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 15970,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.46834375382144e+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 sha256:11e5f5374413173fb4a1b7e42ba0060c3d5a0137bb62d4241906640eb26e1678
+size 5112