comodoro's picture
Model with more data
ca1377c
#!/usr/bin/env python3
from datasets import load_dataset, load_metric, Audio, Dataset
from transformers import pipeline, AutoFeatureExtractor, AutoTokenizer, Wav2Vec2ForCTC
import os
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 = {
'ü': 'ue',
'ö': 'oe',
'ï': 'i',
'ë': 'e',
'ä': 'ae',
'ã': 'a',
'à': 'á',
'ø': 'o',
'è': 'é',
'ê': 'é',
'å': 'ó',
'î': 'i',
'ñ': 'ň',
'ç': 's',
'ľ': 'l',
'ż': 'ž',
'ł': 'w',
'ć': 'č',
'þ': 't',
'ß': 'ss',
'ę': 'en',
'ą': 'an',
'æ': 'ae',
}
def replace_chars(sentence):
result = ''
for ch in sentence:
new = CHARS[ch] if ch in CHARS else ch
result += new
return result
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)
text = replace_chars(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
if args.limit:
dataset = dataset.select(range(limit))
feature_extractor = AutoFeatureExtractor.from_pretrained(args.model_id)
# load processor
sampling_rate = feature_extractor.sampling_rate
# resample audio
dataset = dataset.cast_column("audio", Audio(sampling_rate=sampling_rate))
asr = None
if os.path.exists(args.model_id):
model = Wav2Vec2ForCTC.from_pretrained(args.model_id)
tokenizer = AutoTokenizer.from_pretrained(args.model_id)
# load eval pipeline
asr = pipeline("automatic-speech-recognition", model=model, tokenizer=tokenizer, feature_extractor=feature_extractor)
else:
asr = pipeline("automatic-speech-recognition", model=args.model_id)
# 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."
)
parser.add_argument(
"--limit", type=int, help="Not required. If greater than zero, select a subset of this size from the dataset.", default=0
)
args = parser.parse_args()
main(args)