Eduardo Gonzalez Ponferrada

Add wav2vec model with LM

99b5a70 about 2 years ago

No virus

6.17 kB

	#!/usr/bin/env python3
	from datasets import load_dataset, load_metric, Audio, Dataset
	from transformers import pipeline, AutoFeatureExtractor
	import re
	import argparse
	import unicodedata
	from typing import Dict


	def log_results(result: Dataset, args: Dict[str, str]):
	""" DO NOT CHANGE. This function computes and logs the result metrics. """

	log_outputs = args.log_outputs
	dataset_id = "_".join(args.dataset.split("/") + [args.config, args.split])

	# load metric
	wer = load_metric("wer")
	cer = load_metric("cer")

	# compute metrics
	wer_result = wer.compute(references=result["target"], predictions=result["prediction"])
	cer_result = cer.compute(references=result["target"], predictions=result["prediction"])

	# print & log results
	result_str = (
	f"WER: {wer_result}\n"
	f"CER: {cer_result}"
	)
	print(result_str)

	with open(f"{dataset_id}_eval_results.txt", "w") as f:
	f.write(result_str)

	# log all results in text file. Possibly interesting for analysis
	if log_outputs is not None:
	pred_file = f"log_{dataset_id}_predictions.txt"
	target_file = f"log_{dataset_id}_targets.txt"

	with open(pred_file, "w") as p, open(target_file, "w") as t:

	# mapping function to write output
	def write_to_file(batch, i):
	p.write(f"{i}" + "\n")
	p.write(batch["prediction"] + "\n")
	t.write(f"{i}" + "\n")
	t.write(batch["target"] + "\n")

	result.map(write_to_file, with_indices=True)


	def normalize_text(text: str) -> str:
	""" DO ADAPT FOR YOUR USE CASE. this function normalizes the target text. """

	# chars_to_ignore_regex = '[,?.!\-\;\:\"“%‘”�—’…–]' # noqa: W605 IMPORTANT: this should correspond to the chars that were ignored during training
	chars_to_ignore_regex = ',\?\¿\.\!\¡\;\；\:\""\%\"\�\ʿ\·\჻\~\՞\؟\،\।\॥\«\»\„\“\”\「\」\‘\’\《\》\[\]\{\}\=\`\_\+\<\>\…\–\°\´\ʾ\‹\›\©\®\—\→\。\、\﹂\﹁\‧\～\﹏\，\｛\｝\（\）\［\］\【\】\‥\〽\『\』\〝\〟\⟨\⟩\〜\：\！\？\♪\؛\/\\\º\−\^\ʻ\ˆ\≪\≫'
	chars_to_ignore_regex += "$\&\'\-\\|\¨\ª\ß\à\â\ã\ä\å\æ\ç\ê\ë\ì\î\ï\ð\ò\ô\õ\ö\ø\ù\û\ý\þ\ā\ă\ć\č\đ\ė\ę\ě\ğ\ī\ı\ł\ń\ō\ŏ\ő\œ\ř\ś\ş\š\ū\ź\ż\ž\ș\ț\ə\ʷ\ʽ\ː\́\̇\ϙ\а\б\в\г\д\е\и\й\к\л\н\о\п\р\с\т\ч\ш\ы\ь\ю\я\ё\ү\ө\ְ\ִ\ֵ\ָ\ֹ\ּ\ב\ה\ו\י\כ\ל\ם\מ\נ\ס\ק\ר\ש\ת\ا\ب\ة\د\ذ\ر\ل\م\ه\و\ي\ਆ\ਘ\ਤ\ਨ\ਮ\ਸ\ਾ\ਿ\ੰ\ṁ\ṃ\ṇ\ồ\‐\‑\―\し\の\ひ\ら\ゴ\ヒ\ミ\ム\ラ\㓁\口\周\夷\山\戌\日\本\比\毵\消\生\申\真\箱\网\罒\罓\肋\肌\背\良\蝦\鮓\鮨\ﬁ\$\&\'\-\\|\¨\ª\ß\à\â\ã\ä\å\æ\ç\ê\ë\ì\î\ï\ð\ò\ô\õ\ö\ø\ù\û\ý\þ\ā\ă\ć\č\đ\ė\ę\ě\ğ\ī\ı\ł\ń\ō\ŏ\ő\œ\ř\ś\ş\š\ū\ź\ż\ž\ș\ț\ə\ʷ\ʽ\ː\́\̇\ϙ\а\б\в\г\д\е\и\й\к\л\н\о\п\р\с\т\ч\ш\ы\ь\ю\я\ё\ү\ө\ְ\ִ\ֵ\ָ\ֹ\ּ\ב\ה\ו\י\כ\ל\ם\מ\נ\ס\ק\ר\ש\ת\ا\ب\ة\د\ذ\ر\ل\م\ه\و\ي\ਆ\ਘ\ਤ\ਨ\ਮ\ਸ\ਾ\ਿ\ੰ\ṁ\ṃ\ṇ\ồ\‐\‑\―\し\の\ひ\ら\ゴ\ヒ\ミ\ム\ラ\㓁\口\周\夷\山\戌\日\本\比\毵\消\生\申\真\箱\网\罒\罓\肋\肌\背\良\蝦\鮓\鮨\ﬁ\"
	chars_to_ignore_regex = "[" + chars_to_ignore_regex + "]"

	text = text.lower()
	# normalize non-standard (stylized) unicode characters
	text = unicodedata.normalize('NFKC', text)
	# remove punctuation
	text = re.sub(chars_to_ignore_regex, "", text)

	# Let's also make sure we split on all kinds of newlines, spaces, etc...
	text = " ".join(text.split())

	return text


	def main(args):
	# load dataset
	dataset = load_dataset(args.dataset, args.config, split=args.split, use_auth_token=True)

	# for testing: only process the first two examples as a test
	# dataset = dataset.select(range(10))

	# load processor
	feature_extractor = AutoFeatureExtractor.from_pretrained(args.model_id)
	sampling_rate = feature_extractor.sampling_rate

	# resample audio
	dataset = dataset.cast_column("audio", Audio(sampling_rate=sampling_rate))

	# load eval pipeline
	# asr = pipeline("automatic-speech-recognition", model=args.model_id)
	asr = pipeline("automatic-speech-recognition", model=args.model_id, device=0)

	# map function to decode audio
	def map_to_pred(batch):
	prediction = asr(batch["audio"]["array"], chunk_length_s=args.chunk_length_s, stride_length_s=args.stride_length_s)

	batch["prediction"] = prediction["text"]
	batch["target"] = normalize_text(batch["sentence"])
	return batch

	# run inference on all examples
	result = dataset.map(map_to_pred, remove_columns=dataset.column_names)

	# compute and log_results
	# do not change function below
	log_results(result, args)


	if __name__ == "__main__":
	parser = argparse.ArgumentParser()

	parser.add_argument(
	"--model_id", type=str, required=True, help="Model identifier. Should be loadable with 🤗 Transformers"
	)
	parser.add_argument(
	"--dataset", type=str, required=True, help="Dataset name to evaluate the `model_id`. Should be loadable with 🤗 Datasets"
	)
	parser.add_argument(
	"--config", type=str, required=True, help="Config of the dataset. E.g. `'en'` for Common Voice"
	)
	parser.add_argument(
	"--split", type=str, required=True, help="Split of the dataset. E.g. `'test'`"
	)
	parser.add_argument(
	"--chunk_length_s", type=float, default=None, help="Chunk length in seconds. Defaults to None. For long audio files a good value would be 5.0 seconds."
	)
	parser.add_argument(
	"--stride_length_s", type=float, default=None, help="Stride of the audio chunks. Defaults to None. For long audio files a good value would be 1.0 seconds."
	)
	parser.add_argument(
	"--log_outputs", action='store_true', help="If defined, write outputs to log file for analysis."
	)
	args = parser.parse_args()

	main(args)