End of training

README.md

@@ -0,0 +1,86 @@
+---
+license: mit
+base_model: distil-whisper/distil-small.en
+tags:
+- generated_from_trainer
+datasets:
+- speech_commands
+metrics:
+- accuracy
+model-index:
+- name: distil-small.en-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: 0.8066546762589928
+---
+
+<!-- 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. -->
+
+# distil-small.en-speech-commands
+
+This model is a fine-tuned version of [distil-whisper/distil-small.en](https://huggingface.co/distil-whisper/distil-small.en) on the speech_commands dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9307
+- Accuracy: 0.8067
+
+## 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: 64
+- eval_batch_size: 64
+- 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.1861        | 1.0   | 618  | 0.7743          | 0.8022   |
+| 0.1135        | 2.0   | 1236 | 0.9853          | 0.8049   |
+| 0.078         | 3.0   | 1854 | 0.9307          | 0.8067   |
+| 0.038         | 4.0   | 2472 | 0.9989          | 0.8049   |
+| 0.0375        | 5.0   | 3090 | 1.0738          | 0.8035   |
+| 0.0462        | 6.0   | 3708 | 1.1601          | 0.8067   |
+| 0.018         | 7.0   | 4326 | 1.5369          | 0.8067   |
+| 0.0008        | 8.0   | 4944 | 1.2515          | 0.8067   |
+| 0.0016        | 9.0   | 5562 | 1.3494          | 0.8058   |
+| 0.0002        | 10.0  | 6180 | 1.5117          | 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 +1,224 @@
+{
+  "_name_or_path": "distil-whisper/distil-small.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": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 50257,
+  "dropout": 0.0,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 50256,
+  "forced_decoder_ids": [
+    [
+      1,
+      50362
+    ]
+  ],
+  "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"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "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"
+  },
+  "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": 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": "4.43.3",
+  "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:f5daf49814a5467286b56cf366fd5968caee96abaf5240a3205283519e01cc39
+size 353461320

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/Oct01_09-00-37_ki-g0010/events.out.tfevents.1727773242.ki-g0010.1531976.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd01e1b3f3013d4df2b3840b34759d307e29723eb2183efd74a2ad1266420d1
+size 7920

runs/Oct01_09-13-46_ki-g0010/events.out.tfevents.1727774030.ki-g0010.1544271.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eafe65c6ccd53f121038364f106f4bfdcae0c26420695e63e4df8b3d8f5e7d6e
+size 272200

runs/Oct01_09-13-46_ki-g0010/events.out.tfevents.1727777698.ki-g0010.1544271.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13f350391f13a729c2e2503ca6208827c3e18b1dedc1221315030641c5d7ab22
+size 411

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813a3959e2b9ade69fb6372ab4206321ccbaf0eddfada2987c9fce838799bf75
+size 5240