pip install transformers datasets evaluate soundfile librosa torchcodec

>>> from huggingface_hub import notebook_login

>>> notebook_login()

>>> from datasets import load_dataset, Audio

>>> minds = load_dataset("PolyAI/minds14", name="en-US", split="train")

>>> minds = minds.train_test_split(test_size=0.2)

>>> minds
DatasetDict({
    train: Dataset({
        features: ['path', 'audio', 'transcription', 'english_transcription', 'intent_class', 'lang_id'],
        num_rows: 450
    })
    test: Dataset({
        features: ['path', 'audio', 'transcription', 'english_transcription', 'intent_class', 'lang_id'],
        num_rows: 113
    })
})

>>> minds = minds.remove_columns(["path", "transcription", "english_transcription", "lang_id"])

>>> minds["train"][0]
{'audio': {'array': array([ 0.        ,  0.        ,  0.        , ..., -0.00048828,
         -0.00024414, -0.00024414], dtype=float32),
  'path': '/root/.cache/huggingface/datasets/downloads/extracted/f14948e0e84be638dd7943ac36518a4cf3324e8b7aa331c5ab11541518e9368c/en-US~APP_ERROR/602b9a5fbb1e6d0fbce91f52.wav',
  'sampling_rate': 8000},
 'intent_class': 2}

>>> labels = minds["train"].features["intent_class"].names
>>> label2id, id2label = dict(), dict()
>>> for i, label in enumerate(labels):
...     label2id[label] = str(i)
...     id2label[str(i)] = label

>>> id2label[str(2)]
'app_error'

>>> from transformers import AutoFeatureExtractor

>>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/wav2vec2-base")

>>> minds = minds.cast_column("audio", Audio(sampling_rate=16_000))
>>> minds["train"][0]
{'audio': {'array': array([ 2.2098757e-05,  4.6582241e-05, -2.2803260e-05, ...,
         -2.8419291e-04, -2.3305941e-04, -1.1425107e-04], dtype=float32),
  'path': '/root/.cache/huggingface/datasets/downloads/extracted/f14948e0e84be638dd7943ac36518a4cf3324e8b7aa331c5ab11541518e9368c/en-US~APP_ERROR/602b9a5fbb1e6d0fbce91f52.wav',
  'sampling_rate': 16000},
 'intent_class': 2}

>>> def preprocess_function(examples):
...     audio_arrays = [x["array"] for x in examples["audio"]]
...     inputs = feature_extractor(
...         audio_arrays, sampling_rate=feature_extractor.sampling_rate, max_length=16000, truncation=True
...     )
...     return inputs

>>> encoded_minds = minds.map(preprocess_function, remove_columns="audio", batched=True)
>>> encoded_minds = encoded_minds.rename_column("intent_class", "label")

>>> import evaluate

>>> accuracy = evaluate.load("accuracy")

>>> import numpy as np


>>> def compute_metrics(eval_pred):
...     predictions = np.argmax(eval_pred.predictions, axis=1)
...     return accuracy.compute(predictions=predictions, references=eval_pred.label_ids)

>>> from transformers import AutoModelForAudioClassification, TrainingArguments, Trainer

>>> num_labels = len(id2label)
>>> model = AutoModelForAudioClassification.from_pretrained(
...     "facebook/wav2vec2-base", num_labels=num_labels, label2id=label2id, id2label=id2label
... )

>>> training_args = TrainingArguments(
...     output_dir="my_awesome_mind_model",
...     eval_strategy="epoch",
...     save_strategy="epoch",
...     learning_rate=3e-5,
...     per_device_train_batch_size=32,
...     gradient_accumulation_steps=4,
...     per_device_eval_batch_size=32,
...     num_train_epochs=10,
...     warmup_steps=0.1,
...     logging_steps=10,
...     load_best_model_at_end=True,
...     metric_for_best_model="accuracy",
...     push_to_hub=True,
...     report_to="trackio",
... )

>>> trainer = Trainer(
...     model=model,
...     args=training_args,
...     train_dataset=encoded_minds["train"],
...     eval_dataset=encoded_minds["test"],
...     processing_class=feature_extractor,
...     compute_metrics=compute_metrics,
... )

>>> trainer.train()

>>> trainer.push_to_hub()

>>> from datasets import load_dataset, Audio

>>> dataset = load_dataset("PolyAI/minds14", name="en-US", split="train")
>>> dataset = dataset.cast_column("audio", Audio(sampling_rate=16000))
>>> sampling_rate = dataset.features["audio"].sampling_rate
>>> audio_file = dataset[0]["audio"]["path"]

>>> from transformers import pipeline

>>> classifier = pipeline("audio-classification", model="stevhliu/my_awesome_minds_model")
>>> classifier(audio_file)
[
    {'score': 0.09766869246959686, 'label': 'cash_deposit'},
    {'score': 0.07998877018690109, 'label': 'app_error'},
    {'score': 0.0781070664525032, 'label': 'joint_account'},
    {'score': 0.07667109370231628, 'label': 'pay_bill'},
    {'score': 0.0755252093076706, 'label': 'balance'}
]

>>> from transformers import AutoFeatureExtractor

>>> feature_extractor = AutoFeatureExtractor.from_pretrained("stevhliu/my_awesome_minds_model")
>>> inputs = feature_extractor(dataset[0]["audio"]["array"], sampling_rate=sampling_rate, return_tensors="pt")

>>> from transformers import AutoModelForAudioClassification

>>> model = AutoModelForAudioClassification.from_pretrained("stevhliu/my_awesome_minds_model")
>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> import torch

>>> predicted_class_ids = torch.argmax(logits).item()
>>> predicted_label = model.config.id2label[predicted_class_ids]
>>> predicted_label
'cash_deposit'