pip install transformers datasets evaluate jiwer 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[:100]")

>>> 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: 16
    })
    test: Dataset({
        features: ['path', 'audio', 'transcription', 'english_transcription', 'intent_class', 'lang_id'],
        num_rows: 4
    })
})

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

>>> minds["train"][0]
{'audio': {'array': array([-0.00024414,  0.        ,  0.        , ...,  0.00024414,
          0.00024414,  0.00024414], dtype=float32),
  'path': '/root/.cache/huggingface/datasets/downloads/extracted/f14948e0e84be638dd7943ac36518a4cf3324e8b7aa331c5ab11541518e9368c/en-US~APP_ERROR/602ba9e2963e11ccd901cd4f.wav',
  'sampling_rate': 8000},
 'path': '/root/.cache/huggingface/datasets/downloads/extracted/f14948e0e84be638dd7943ac36518a4cf3324e8b7aa331c5ab11541518e9368c/en-US~APP_ERROR/602ba9e2963e11ccd901cd4f.wav',
 'transcription': "hi I'm trying to use the banking app on my phone and currently my checking and savings account balance is not refreshing"}

>>> from transformers import AutoProcessor

>>> processor = AutoProcessor.from_pretrained("facebook/wav2vec2-base")

>>> minds = minds.cast_column("audio", Audio(sampling_rate=16_000))
>>> minds["train"][0]
{'audio': {'array': array([-2.38064706e-04, -1.58618059e-04, -5.43987835e-06, ...,
          2.78103951e-04,  2.38446111e-04,  1.18740834e-04], dtype=float32),
  'path': '/root/.cache/huggingface/datasets/downloads/extracted/f14948e0e84be638dd7943ac36518a4cf3324e8b7aa331c5ab11541518e9368c/en-US~APP_ERROR/602ba9e2963e11ccd901cd4f.wav',
  'sampling_rate': 16000},
 'path': '/root/.cache/huggingface/datasets/downloads/extracted/f14948e0e84be638dd7943ac36518a4cf3324e8b7aa331c5ab11541518e9368c/en-US~APP_ERROR/602ba9e2963e11ccd901cd4f.wav',
 'transcription': "hi I'm trying to use the banking app on my phone and currently my checking and savings account balance is not refreshing"}

>>> def uppercase(example):
...     return {"transcription": example["transcription"].upper()}


>>> minds = minds.map(uppercase)

>>> def prepare_dataset(batch):
...     audio = batch["audio"]
...     batch = processor(audio["array"], sampling_rate=audio["sampling_rate"], text=batch["transcription"])
...     batch["input_length"] = len(batch["input_values"][0])
...     return batch

>>> encoded_minds = minds.map(prepare_dataset, remove_columns=minds.column_names["train"], num_proc=4)

>>> import torch

>>> from dataclasses import dataclass, field
>>> from typing import Any, Dict, List, Optional, Union


>>> @dataclass
... class DataCollatorCTCWithPadding:
...     processor: AutoProcessor
...     padding: Union[bool, str] = "longest"

...     def __call__(self, features: list[dict[str, Union[list[int], torch.Tensor]]]) -> dict[str, torch.Tensor]:
...         # split inputs and labels since they have to be of different lengths and need
...         # different padding methods
...         input_features = [{"input_values": feature["input_values"][0]} for feature in features]
...         label_features = [{"input_ids": feature["labels"]} for feature in features]

...         batch = self.processor.pad(input_features, padding=self.padding, return_tensors="pt")

...         labels_batch = self.processor.pad(labels=label_features, padding=self.padding, return_tensors="pt")

...         # replace padding with -100 to ignore loss correctly
...         labels = labels_batch["input_ids"].masked_fill(labels_batch.attention_mask.ne(1), -100)

...         batch["labels"] = labels

...         return batch

>>> data_collator = DataCollatorCTCWithPadding(processor=processor, padding="longest")

>>> import evaluate

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

>>> import numpy as np


>>> def compute_metrics(pred):
...     pred_logits = pred.predictions
...     pred_ids = np.argmax(pred_logits, axis=-1)

...     pred.label_ids[pred.label_ids == -100] = processor.tokenizer.pad_token_id

...     pred_str = processor.batch_decode(pred_ids)
...     label_str = processor.batch_decode(pred.label_ids, group_tokens=False)

...     wer_score = wer.compute(predictions=pred_str, references=label_str)

...     return {"wer": wer_score}

>>> from transformers import AutoModelForCTC, TrainingArguments, Trainer

>>> model = AutoModelForCTC.from_pretrained(
...     "facebook/wav2vec2-base",
...     ctc_loss_reduction="mean",
...     pad_token_id=processor.tokenizer.pad_token_id,
... )

>>> training_args = TrainingArguments(
...     output_dir="my_awesome_asr_mind_model",
...     per_device_train_batch_size=8,
...     gradient_accumulation_steps=2,
...     learning_rate=1e-5,
...     warmup_steps=500,
...     max_steps=2000,
...     gradient_checkpointing=True,
...     fp16=True,
...     train_sampling_strategy="group_by_length",
...     eval_strategy="steps",
...     per_device_eval_batch_size=8,
...     save_steps=1000,
...     eval_steps=1000,
...     logging_steps=25,
...     load_best_model_at_end=True,
...     metric_for_best_model="wer",
...     greater_is_better=False,
...     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=processor,
...     data_collator=data_collator,
...     compute_metrics=compute_metrics,
... )

>>> trainer.train()

>>> trainer.push_to_hub()

>>> from datasets import load_dataset, Audio

>>> dataset = load_dataset("PolyAI/minds14", "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

>>> transcriber = pipeline("automatic-speech-recognition", model="stevhliu/my_awesome_asr_minds_model")
>>> transcriber(audio_file)
{'text': 'I WOUD LIKE O SET UP JOINT ACOUNT WTH Y PARTNER'}

>>> from transformers import AutoProcessor

>>> processor = AutoProcessor.from_pretrained("stevhliu/my_awesome_asr_mind_model")
>>> inputs = processor(dataset[0]["audio"]["array"], sampling_rate=sampling_rate, return_tensors="pt")

>>> from transformers import AutoModelForCTC

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

>>> import torch

>>> predicted_ids = torch.argmax(logits, dim=-1)
>>> transcription = processor.batch_decode(predicted_ids)
>>> transcription
['I WOUL LIKE O SET UP JOINT ACOUNT WTH Y PARTNER']