File size: 6,543 Bytes
cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c efbb55a cd4ae0c 32f1217 e904c32 cd4ae0c 32f1217 cd4ae0c e904c32 cd4ae0c 32f1217 e904c32 cd4ae0c e904c32 cd4ae0c 32f1217 e904c32 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 cd4ae0c 32f1217 e904c32 32f1217 e904c32 32f1217 e904c32 32f1217 e904c32 32f1217 cd4ae0c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 |
---
language: ar
datasets:
- common_voice
- arabic_speech_corpus
metrics:
- wer
tags:
- audio
- automatic-speech-recognition
- speech
- xlsr-fine-tuning-week
license: apache-2.0
model-index:
- name: elgeish XLSR Wav2Vec2 Large 53
results:
- task:
name: Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice ar
type: common_voice
args: ar
metrics:
- name: Test WER
type: wer
value: 26.55
---
# Wav2Vec2-Large-XLSR-53-Arabic
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53)
on Arabic using the [Common Voice](https://huggingface.co/datasets/common_voice)
and the [Arabic Speech Corpus](https://huggingface.co/datasets/arabic_speech_corpus) datasets.
When using this model, make sure that your speech input is sampled at 16kHz.
## Usage
The model can be used directly (without a language model) as follows:
```python
import torch
import torchaudio
from datasets import load_dataset
from lang_trans.arabic import buckwalter
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
dataset = load_dataset("common_voice", "ar", split="test[:10]")
resamplers = { # all three sampling rates exist in test split
48000: torchaudio.transforms.Resample(48000, 16000),
44100: torchaudio.transforms.Resample(44100, 16000),
32000: torchaudio.transforms.Resample(32000, 16000),
}
def prepare_example(example):
speech, sampling_rate = torchaudio.load(example["path"])
example["speech"] = resamplers[sampling_rate](speech).squeeze().numpy()
return example
dataset = dataset.map(prepare_example)
processor = Wav2Vec2Processor.from_pretrained("elgeish/wav2vec2-large-xlsr-53-arabic")
model = Wav2Vec2ForCTC.from_pretrained("elgeish/wav2vec2-large-xlsr-53-arabic").eval()
def predict(batch):
inputs = processor(batch["speech"], sampling_rate=16000, return_tensors="pt", padding=True)
with torch.no_grad():
predicted = torch.argmax(model(inputs.input_values).logits, dim=-1)
predicted[predicted == -100] = processor.tokenizer.pad_token_id # see fine-tuning script
batch["predicted"] = processor.tokenizer.batch_decode(predicted)
return batch
dataset = dataset.map(predict, batched=True, batch_size=1, remove_columns=["speech"])
for reference, predicted in zip(dataset["sentence"], dataset["predicted"]):
print("reference:", reference)
print("predicted:", buckwalter.untrans(predicted))
print("--")
```
Here's the output:
```
reference: ألديك قلم ؟
predicted: هلديك قالر
--
reference: ليست هناك مسافة على هذه الأرض أبعد من يوم أمس.
predicted: ليست نالك مسافة على هذه الأرض أبعد من يوم أمس
--
reference: إنك تكبر المشكلة.
predicted: إنك تكبر المشكلة
--
reference: يرغب أن يلتقي بك.
predicted: يرغب أن يلتقي بك
--
reference: إنهم لا يعرفون لماذا حتى.
predicted: إنهم لا يعرفون لماذا حتى
--
reference: سيسعدني مساعدتك أي وقت تحب.
predicted: سيسئدني مساعد سكرأي وقت تحب
--
reference: أَحَبُّ نظريّة علمية إليّ هي أن حلقات زحل مكونة بالكامل من الأمتعة المفقودة.
predicted: أحب ناضريةً علمية إلي هي أنحل قتزح المكونا بالكامل من الأمت عن المفقودة
--
reference: سأشتري له قلماً.
predicted: سأشتري له قلما
--
reference: أين المشكلة ؟
predicted: أين المشكل
--
reference: وَلِلَّهِ يَسْجُدُ مَا فِي السَّمَاوَاتِ وَمَا فِي الْأَرْضِ مِنْ دَابَّةٍ وَالْمَلَائِكَةُ وَهُمْ لَا يَسْتَكْبِرُونَ
predicted: ولله يسجد ما في السماوات وما في الأرض من دابة والملائكة وهم لا يستكبرون
--
```
## Evaluation
The model can be evaluated as follows on the Arabic test data of Common Voice:
```python
import jiwer
import torch
import torchaudio
from datasets import load_dataset
from lang_trans.arabic import buckwalter
from transformers import set_seed, Wav2Vec2ForCTC, Wav2Vec2Processor
set_seed(42)
test_split = load_dataset("common_voice", "ar", split="test")
resamplers = { # all three sampling rates exist in test split
48000: torchaudio.transforms.Resample(48000, 16000),
44100: torchaudio.transforms.Resample(44100, 16000),
32000: torchaudio.transforms.Resample(32000, 16000),
}
def prepare_example(example):
speech, sampling_rate = torchaudio.load(example["path"])
example["speech"] = resamplers[sampling_rate](speech).squeeze().numpy()
return example
test_split = test_split.map(prepare_example)
processor = Wav2Vec2Processor.from_pretrained("elgeish/wav2vec2-large-xlsr-53-arabic")
model = Wav2Vec2ForCTC.from_pretrained("elgeish/wav2vec2-large-xlsr-53-arabic").to("cuda").eval()
def predict(batch):
inputs = processor(batch["speech"], sampling_rate=16000, return_tensors="pt", padding=True)
with torch.no_grad():
predicted = torch.argmax(model(inputs.input_values.to("cuda")).logits, dim=-1)
predicted[predicted == -100] = processor.tokenizer.pad_token_id # see fine-tuning script
batch["predicted"] = processor.batch_decode(predicted)
return batch
test_split = test_split.map(predict, batched=True, batch_size=16, remove_columns=["speech"])
transformation = jiwer.Compose([
# normalize some diacritics, remove punctuation, and replace Persian letters with Arabic ones
jiwer.SubstituteRegexes({
r'[auiFNKo\~_،؟»\?;:\-,\.؛«!"]': "", "\u06D6": "",
r"[\|\{]": "A", "p": "h", "ک": "k", "ی": "y"}),
# default transformation below
jiwer.RemoveMultipleSpaces(),
jiwer.Strip(),
jiwer.SentencesToListOfWords(),
jiwer.RemoveEmptyStrings(),
])
metrics = jiwer.compute_measures(
truth=[buckwalter.trans(s) for s in test_split["sentence"]], # Buckwalter transliteration
hypothesis=test_split["predicted"],
truth_transform=transformation,
hypothesis_transform=transformation,
)
print(f"WER: {metrics['wer']:.2%}")
```
**Test Result**: 26.55%
## Training
You can find the script used to produce this model
[here](https://github.com/elgeish/transformers/blob/cfc0bd01f2ac2ea3a5acc578ef2e204bf4304de7/examples/research_projects/wav2vec2/finetune_base_arabic_speech_corpus.sh).
|