initial commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+base_model: openai/whisper-medium.en
+tags:
+- generated_from_trainer
+datasets:
+- marsyas/gtzan
+metrics:
+- accuracy
+model-index:
+- name: whisper-medium.en-finetuned-gtzan
+  results:
+  - task:
+      name: Audio Classification
+      type: audio-classification
+    dataset:
+      name: GTZAN
+      type: marsyas/gtzan
+      config: all
+      split: train
+      args: all
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.95
+---
+
+<!-- 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. -->
+
+# whisper-medium.en-finetuned-gtzan
+
+This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on the GTZAN dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2885
+- Accuracy: 0.95
+
+## 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 16
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.7711        | 1.0   | 112  | 1.6556          | 0.52     |
+| 0.5477        | 2.0   | 225  | 0.4738          | 0.85     |
+| 0.535         | 3.0   | 337  | 0.3137          | 0.92     |
+| 0.231         | 4.0   | 450  | 0.3613          | 0.9      |
+| 0.1923        | 5.0   | 562  | 0.2885          | 0.95     |
+| 0.0584        | 6.0   | 675  | 0.6531          | 0.86     |
+| 0.1783        | 7.0   | 787  | 0.5717          | 0.9      |
+| 0.0022        | 8.0   | 900  | 0.4205          | 0.91     |
+| 0.1032        | 9.0   | 1012 | 0.4984          | 0.91     |
+| 0.0011        | 10.0  | 1125 | 0.3778          | 0.94     |
+| 0.0104        | 11.0  | 1237 | 0.3709          | 0.94     |
+| 0.0011        | 12.0  | 1350 | 0.4564          | 0.92     |
+| 0.0009        | 13.0  | 1462 | 0.3796          | 0.94     |
+| 0.0008        | 14.0  | 1575 | 0.3880          | 0.94     |
+| 0.0008        | 15.0  | 1687 | 0.3930          | 0.94     |
+| 0.0008        | 15.93 | 1792 | 0.3955          | 0.94     |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.2+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,172 @@
+{
+  "_name_or_path": "openai/whisper-medium.en",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForAudioClassification"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50256
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 50257,
+  "dropout": 0.0,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 24,
+  "eos_token_id": 50256,
+  "forced_decoder_ids": [
+    [
+      1,
+      50362
+    ]
+  ],
+  "id2label": {
+    "0": "blues",
+    "1": "classical",
+    "2": "country",
+    "3": "disco",
+    "4": "hiphop",
+    "5": "jazz",
+    "6": "metal",
+    "7": "pop",
+    "8": "reggae",
+    "9": "rock"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "blues": "0",
+    "classical": "1",
+    "country": "2",
+    "disco": "3",
+    "hiphop": "4",
+    "jazz": "5",
+    "metal": "6",
+    "pop": "7",
+    "reggae": "8",
+    "rock": "9"
+  },
+  "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": 24,
+  "num_mel_bins": 80,
+  "pad_token_id": 50256,
+  "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,
+    357,
+    366,
+    438,
+    532,
+    685,
+    705,
+    796,
+    930,
+    1058,
+    1220,
+    1267,
+    1279,
+    1303,
+    1343,
+    1377,
+    1391,
+    1635,
+    1782,
+    1875,
+    2162,
+    2361,
+    2488,
+    3467,
+    4008,
+    4211,
+    4600,
+    4808,
+    5299,
+    5855,
+    6329,
+    7203,
+    9609,
+    9959,
+    10563,
+    10786,
+    11420,
+    11709,
+    11907,
+    13163,
+    13697,
+    13700,
+    14808,
+    15306,
+    16410,
+    16791,
+    17992,
+    19203,
+    19510,
+    20724,
+    22305,
+    22935,
+    27007,
+    30109,
+    30420,
+    33409,
+    34949,
+    40283,
+    40493,
+    40549,
+    47282,
+    49146,
+    50257,
+    50357,
+    50358,
+    50359,
+    50360,
+    50361
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51864
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bbb0c9771510c42e97b176e5eadfc5afc444101626fe8795596600d7490a7ea
+size 1229966128

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
+}

runs/Dec21_13-11-03_Christians-Desktop/events.out.tfevents.1703160675.Christians-Desktop.269605.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b88f9732dc3f2e65ab40c3b6066598d5b18e371c42b3fb15db1c6320bd484255
+size 47768

runs/Dec21_13-11-03_Christians-Desktop/events.out.tfevents.1703206016.Christians-Desktop.269605.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9333a863cf36b725451a48ff5123727f4374fc5699a5ac1481d0afb4227558af
+size 411

runs/Dec25_00-13-11_Christians-Desktop/events.out.tfevents.1703459600.Christians-Desktop.50576.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfaf2966d6c294291c5d9da5bf56f64faa501bd164b4fa540ae07d847af11507
+size 12834

runs/Dec25_00-28-21_Christians-Desktop/events.out.tfevents.1703460505.Christians-Desktop.53729.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60bc4c3ee6b4d5fc82c1f57ab1c7d276005e8dd737304339827c4e954607873f
+size 12701

runs/Dec25_00-46-03_Christians-Desktop/events.out.tfevents.1703461567.Christians-Desktop.57171.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e7a369c9114bdbac23d46e61999bbae4fbe355b465f45a681d6d0dde4f25d2
+size 68058

runs/Dec25_00-46-03_Christians-Desktop/events.out.tfevents.1703465232.Christians-Desktop.57171.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57bcfcbbe1c03f43746b9ee2d5b70c4bc5f96ebae9a44fc8fce9ff2ac4214094
+size 411

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc0cb94984e1ad0b2c72ffeb1c5a9c5818fe85ee3d3e4c5f659cbbd0791b131
+size 4728