|
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])
|
|
|
|
|
|
wer = load_metric("wer")
|
|
cer = load_metric("cer")
|
|
|
|
pred_string = [element.lower() for element in result["prediction"]]
|
|
actual = [element.lower() for element in result["target"]]
|
|
|
|
|
|
wer_result = wer.compute(references=actual, predictions=pred_string)
|
|
cer_result = cer.compute(references=actual, predictions=pred_string)
|
|
|
|
|
|
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)
|
|
|
|
|
|
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:
|
|
|
|
|
|
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 = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\'\...\…\–\é\-\„\—\|\/]'
|
|
|
|
text = re.sub(r'[ʻʽʼ‘’´`]', r"'", text)
|
|
text = re.sub(chars_to_ignore_regex, "", text).lower().strip()
|
|
text = re.sub(r"([b-df-hj-np-tv-z])' ([aeiou])", r"\1'\2", text)
|
|
text = re.sub(r"(-| '|' | +)", " ", text)
|
|
|
|
return text
|
|
|
|
|
|
def main(args):
|
|
|
|
dataset = load_dataset(args.dataset, args.config, split=args.split, use_auth_token=True)
|
|
|
|
|
|
|
|
|
|
|
|
feature_extractor = AutoFeatureExtractor.from_pretrained(args.model_id)
|
|
sampling_rate = feature_extractor.sampling_rate
|
|
|
|
|
|
dataset = dataset.cast_column("audio", Audio(sampling_rate=16_000))
|
|
|
|
|
|
asr = pipeline("automatic-speech-recognition", model=args.model_id)
|
|
|
|
|
|
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
|
|
|
|
|
|
result = dataset.map(map_to_pred, remove_columns=dataset.column_names)
|
|
|
|
|
|
|
|
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)
|
|
|
|
|
