Spaces:
Runtime error
Runtime error
File size: 3,791 Bytes
9cd3f2d e3ab055 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 |
import gradio as gr
gr.load("models/m3hrdadfi/wav2vec2-large-xlsr-persian").launch()
import librosa
import torch
import torchaudio
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
from datasets import load_dataset
import numpy as np
import hazm
import re
import string
import IPython.display as ipd
_normalizer = hazm.Normalizer()
chars_to_ignore = [
",", "?", ".", "!", "-", ";", ":", '""', "%", "'", '"', "�",
"#", "!", "؟", "?", "«", "»", "ء", "،", "(", ")", "؛", "'ٔ", "٬",'ٔ', ",", "?",
".", "!", "-", ";", ":",'"',"“", "%", "‘", "”", "�", "–", "…", "_", "”", '“', '„'
]
# In case of farsi
chars_to_ignore = chars_to_ignore + list(string.ascii_lowercase + string.digits)
chars_to_mapping = {
'ك': 'ک', 'دِ': 'د', 'بِ': 'ب', 'زِ': 'ز', 'ذِ': 'ذ', 'شِ': 'ش', 'سِ': 'س', 'ى': 'ی',
'ي': 'ی', 'أ': 'ا', 'ؤ': 'و', "ے": "ی", "ۀ": "ه", "ﭘ": "پ", "ﮐ": "ک", "ﯽ": "ی",
"ﺎ": "ا", "ﺑ": "ب", "ﺘ": "ت", "ﺧ": "خ", "ﺩ": "د", "ﺱ": "س", "ﻀ": "ض", "ﻌ": "ع",
"ﻟ": "ل", "ﻡ": "م", "ﻢ": "م", "ﻪ": "ه", "ﻮ": "و", "ئ": "ی", 'ﺍ': "ا", 'ة': "ه",
'ﯾ': "ی", 'ﯿ': "ی", 'ﺒ': "ب", 'ﺖ': "ت", 'ﺪ': "د", 'ﺮ': "ر", 'ﺴ': "س", 'ﺷ': "ش",
'ﺸ': "ش", 'ﻋ': "ع", 'ﻤ': "م", 'ﻥ': "ن", 'ﻧ': "ن", 'ﻭ': "و", 'ﺭ': "ر", "ﮔ": "گ",
"\u200c": " ", "\u200d": " ", "\u200e": " ", "\u200f": " ", "\ufeff": " ",
}
def multiple_replace(text, chars_to_mapping):
pattern = "|".join(map(re.escape, chars_to_mapping.keys()))
return re.sub(pattern, lambda m: chars_to_mapping[m.group()], str(text))
def remove_special_characters(text, chars_to_ignore_regex):
text = re.sub(chars_to_ignore_regex, '', text).lower() + " "
return text
def normalizer(batch, chars_to_ignore, chars_to_mapping):
chars_to_ignore_regex = f"""[{"".join(chars_to_ignore)}]"""
text = batch["sentence"].lower().strip()
text = _normalizer.normalize(text)
text = multiple_replace(text, chars_to_mapping)
text = remove_special_characters(text, chars_to_ignore_regex)
batch["sentence"] = text
return batch
def speech_file_to_array_fn(batch):
speech_array, sampling_rate = torchaudio.load(batch["path"])
speech_array = speech_array.squeeze().numpy()
speech_array = librosa.resample(np.asarray(speech_array), sampling_rate, 16_000)
batch["speech"] = speech_array
return batch
def predict(batch):
features = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
input_values = features.input_values.to(device)
attention_mask = features.attention_mask.to(device)
with torch.no_grad():
logits = model(input_values, attention_mask=attention_mask).logits
pred_ids = torch.argmax(logits, dim=-1)
batch["predicted"] = processor.batch_decode(pred_ids)[0]
return batch
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
processor = Wav2Vec2Processor.from_pretrained("m3hrdadfi/wav2vec2-large-xlsr-persian")
model = Wav2Vec2ForCTC.from_pretrained("m3hrdadfi/wav2vec2-large-xlsr-persian").to(device)
dataset = load_dataset("common_voice", "fa", split="test[:1%]")
dataset = dataset.map(
normalizer,
fn_kwargs={"chars_to_ignore": chars_to_ignore, "chars_to_mapping": chars_to_mapping},
remove_columns=list(set(dataset.column_names) - set(['sentence', 'path']))
)
dataset = dataset.map(speech_file_to_array_fn)
result = dataset.map(predict)
max_items = np.random.randint(0, len(result), 20).tolist()
for i in max_items:
reference, predicted = result["sentence"][i], result["predicted"][i]
print("reference:", reference)
print("predicted:", predicted)
print('---')
|