初始化项目，由ModelHub XC社区提供模型
Model: jonatasgrosman/wav2vec2-large-xlsr-53-arabic Source: Original Platform
This commit is contained in:
ModelHub XC
17
.gitattributes
vendored
Normal file
17
.gitattributes
vendored
Normal file
@@ -0,0 +1,17 @@
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
200
README.md
Normal file
200
README.md
Normal file
@@ -0,0 +1,200 @@
|
||||
---
|
||||
language: ar
|
||||
datasets:
|
||||
- common_voice
|
||||
- arabic_speech_corpus
|
||||
metrics:
|
||||
- wer
|
||||
- cer
|
||||
tags:
|
||||
- audio
|
||||
- automatic-speech-recognition
|
||||
- speech
|
||||
- xlsr-fine-tuning-week
|
||||
license: apache-2.0
|
||||
model-index:
|
||||
- name: XLSR Wav2Vec2 Arabic by Jonatas Grosman
|
||||
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: 39.59
|
||||
- name: Test CER
|
||||
type: cer
|
||||
value: 18.18
|
||||
---
|
||||
|
||||
# Fine-tuned XLSR-53 large model for speech recognition in Arabic
|
||||
|
||||
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Arabic using the train and validation splits of [Common Voice 6.1](https://huggingface.co/datasets/common_voice) and [Arabic Speech Corpus](https://huggingface.co/datasets/arabic_speech_corpus).
|
||||
When using this model, make sure that your speech input is sampled at 16kHz.
|
||||
|
||||
This model has been fine-tuned thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :)
|
||||
|
||||
The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint
|
||||
|
||||
## Usage
|
||||
|
||||
The model can be used directly (without a language model) as follows...
|
||||
|
||||
Using the [HuggingSound](https://github.com/jonatasgrosman/huggingsound) library:
|
||||
|
||||
```python
|
||||
from huggingsound import SpeechRecognitionModel
|
||||
|
||||
model = SpeechRecognitionModel("jonatasgrosman/wav2vec2-large-xlsr-53-arabic")
|
||||
audio_paths = ["/path/to/file.mp3", "/path/to/another_file.wav"]
|
||||
|
||||
transcriptions = model.transcribe(audio_paths)
|
||||
```
|
||||
|
||||
Writing your own inference script:
|
||||
|
||||
```python
|
||||
import torch
|
||||
import librosa
|
||||
from datasets import load_dataset
|
||||
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
||||
|
||||
LANG_ID = "ar"
|
||||
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-arabic"
|
||||
SAMPLES = 10
|
||||
|
||||
test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
|
||||
|
||||
processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
|
||||
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
|
||||
|
||||
# Preprocessing the datasets.
|
||||
# We need to read the audio files as arrays
|
||||
def speech_file_to_array_fn(batch):
|
||||
speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
|
||||
batch["speech"] = speech_array
|
||||
batch["sentence"] = batch["sentence"].upper()
|
||||
return batch
|
||||
|
||||
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
||||
inputs = processor(test_dataset["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
|
||||
|
||||
with torch.no_grad():
|
||||
logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
|
||||
|
||||
predicted_ids = torch.argmax(logits, dim=-1)
|
||||
predicted_sentences = processor.batch_decode(predicted_ids)
|
||||
|
||||
for i, predicted_sentence in enumerate(predicted_sentences):
|
||||
print("-" * 100)
|
||||
print("Reference:", test_dataset[i]["sentence"])
|
||||
print("Prediction:", predicted_sentence)
|
||||
```
|
||||
|
||||
| Reference | Prediction |
|
||||
| ------------- | ------------- |
|
||||
| ألديك قلم ؟ | ألديك قلم |
|
||||
| ليست هناك مسافة على هذه الأرض أبعد من يوم أمس. | ليست نالك مسافة على هذه الأرض أبعد من يوم الأمس م |
|
||||
| إنك تكبر المشكلة. | إنك تكبر المشكلة |
|
||||
| يرغب أن يلتقي بك. | يرغب أن يلتقي بك |
|
||||
| إنهم لا يعرفون لماذا حتى. | إنهم لا يعرفون لماذا حتى |
|
||||
| سيسعدني مساعدتك أي وقت تحب. | سيسئدنيمساعدتك أي وقد تحب |
|
||||
| أَحَبُّ نظريّة علمية إليّ هي أن حلقات زحل مكونة بالكامل من الأمتعة المفقودة. | أحب نظرية علمية إلي هي أن حل قتزح المكوينا بالكامل من الأمت عن المفقودة |
|
||||
| سأشتري له قلماً. | سأشتري له قلما |
|
||||
| أين المشكلة ؟ | أين المشكل |
|
||||
| وَلِلَّهِ يَسْجُدُ مَا فِي السَّمَاوَاتِ وَمَا فِي الْأَرْضِ مِنْ دَابَّةٍ وَالْمَلَائِكَةُ وَهُمْ لَا يَسْتَكْبِرُونَ | 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 torch
|
||||
import re
|
||||
import librosa
|
||||
from datasets import load_dataset, load_metric
|
||||
from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
|
||||
|
||||
LANG_ID = "ar"
|
||||
MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-arabic"
|
||||
DEVICE = "cuda"
|
||||
|
||||
CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", "；", ":", '""', "%", '"', "<22>", "ʿ", "·", "჻", "~", "՞",
|
||||
"؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
|
||||
"{", "}", "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。",
|
||||
"、", "﹂", "﹁", "‧", "～", "﹏", "，", "｛", "｝", "（", "）", "［", "］", "【", "】", "‥", "〽",
|
||||
"『", "』", "〝", "〟", "⟨", "⟩", "〜", "：", "！", "？", "♪", "؛", "/", "\\", "º", "−", "^", "'", "ʻ", "ˆ"]
|
||||
|
||||
test_dataset = load_dataset("common_voice", LANG_ID, split="test")
|
||||
|
||||
wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
|
||||
cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py
|
||||
|
||||
chars_to_ignore_regex = f"[{re.escape(''.join(CHARS_TO_IGNORE))}]"
|
||||
|
||||
processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
|
||||
model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
|
||||
model.to(DEVICE)
|
||||
|
||||
# Preprocessing the datasets.
|
||||
# We need to read the audio files as arrays
|
||||
def speech_file_to_array_fn(batch):
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("ignore")
|
||||
speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
|
||||
batch["speech"] = speech_array
|
||||
batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"]).upper()
|
||||
return batch
|
||||
|
||||
test_dataset = test_dataset.map(speech_file_to_array_fn)
|
||||
|
||||
# Preprocessing the datasets.
|
||||
# We need to read the audio files as arrays
|
||||
def evaluate(batch):
|
||||
inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
|
||||
|
||||
with torch.no_grad():
|
||||
logits = model(inputs.input_values.to(DEVICE), attention_mask=inputs.attention_mask.to(DEVICE)).logits
|
||||
|
||||
pred_ids = torch.argmax(logits, dim=-1)
|
||||
batch["pred_strings"] = processor.batch_decode(pred_ids)
|
||||
return batch
|
||||
|
||||
result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
||||
|
||||
predictions = [x.upper() for x in result["pred_strings"]]
|
||||
references = [x.upper() for x in result["sentence"]]
|
||||
|
||||
print(f"WER: {wer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")
|
||||
print(f"CER: {cer.compute(predictions=predictions, references=references, chunk_size=1000) * 100}")
|
||||
```
|
||||
|
||||
**Test Result**:
|
||||
|
||||
In the table below I report the Word Error Rate (WER) and the Character Error Rate (CER) of the model. I ran the evaluation script described above on other models as well (on 2021-05-14). Note that the table below may show different results from those already reported, this may have been caused due to some specificity of the other evaluation scripts used.
|
||||
|
||||
| Model | WER | CER |
|
||||
| ------------- | ------------- | ------------- |
|
||||
| jonatasgrosman/wav2vec2-large-xlsr-53-arabic | **39.59%** | **18.18%** |
|
||||
| bakrianoo/sinai-voice-ar-stt | 45.30% | 21.84% |
|
||||
| othrif/wav2vec2-large-xlsr-arabic | 45.93% | 20.51% |
|
||||
| kmfoda/wav2vec2-large-xlsr-arabic | 54.14% | 26.07% |
|
||||
| mohammed/wav2vec2-large-xlsr-arabic | 56.11% | 26.79% |
|
||||
| anas/wav2vec2-large-xlsr-arabic | 62.02% | 27.09% |
|
||||
| elgeish/wav2vec2-large-xlsr-53-arabic | 100.00% | 100.56% |
|
||||
|
||||
## Citation
|
||||
If you want to cite this model you can use this:
|
||||
|
||||
```bibtex
|
||||
@misc{grosman2021xlsr53-large-arabic,
|
||||
title={Fine-tuned {XLSR}-53 large model for speech recognition in {A}rabic},
|
||||
author={Grosman, Jonatas},
|
||||
howpublished={\url{https://huggingface.co/jonatasgrosman/wav2vec2-large-xlsr-53-arabic}},
|
||||
year={2021}
|
||||
}
|
||||
```
|
||||
76
config.json
Normal file
76
config.json
Normal file
@@ -0,0 +1,76 @@
|
||||
{
|
||||
"_name_or_path": "facebook/wav2vec2-large-xlsr-53",
|
||||
"activation_dropout": 0.05,
|
||||
"apply_spec_augment": true,
|
||||
"architectures": [
|
||||
"Wav2Vec2ForCTC"
|
||||
],
|
||||
"attention_dropout": 0.1,
|
||||
"bos_token_id": 1,
|
||||
"conv_bias": true,
|
||||
"conv_dim": [
|
||||
512,
|
||||
512,
|
||||
512,
|
||||
512,
|
||||
512,
|
||||
512,
|
||||
512
|
||||
],
|
||||
"conv_kernel": [
|
||||
10,
|
||||
3,
|
||||
3,
|
||||
3,
|
||||
3,
|
||||
2,
|
||||
2
|
||||
],
|
||||
"conv_stride": [
|
||||
5,
|
||||
2,
|
||||
2,
|
||||
2,
|
||||
2,
|
||||
2,
|
||||
2
|
||||
],
|
||||
"ctc_loss_reduction": "mean",
|
||||
"ctc_zero_infinity": true,
|
||||
"do_stable_layer_norm": true,
|
||||
"eos_token_id": 2,
|
||||
"feat_extract_activation": "gelu",
|
||||
"feat_extract_dropout": 0.0,
|
||||
"feat_extract_norm": "layer",
|
||||
"feat_proj_dropout": 0.05,
|
||||
"final_dropout": 0.0,
|
||||
"gradient_checkpointing": true,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout": 0.05,
|
||||
"hidden_size": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"layerdrop": 0.05,
|
||||
"mask_channel_length": 10,
|
||||
"mask_channel_min_space": 1,
|
||||
"mask_channel_other": 0.0,
|
||||
"mask_channel_prob": 0.0,
|
||||
"mask_channel_selection": "static",
|
||||
"mask_feature_length": 10,
|
||||
"mask_feature_prob": 0.0,
|
||||
"mask_time_length": 10,
|
||||
"mask_time_min_space": 1,
|
||||
"mask_time_other": 0.0,
|
||||
"mask_time_prob": 0.05,
|
||||
"mask_time_selection": "static",
|
||||
"model_type": "wav2vec2",
|
||||
"num_attention_heads": 16,
|
||||
"num_conv_pos_embedding_groups": 16,
|
||||
"num_conv_pos_embeddings": 128,
|
||||
"num_feat_extract_layers": 7,
|
||||
"num_hidden_layers": 24,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.5.0.dev0",
|
||||
"vocab_size": 51
|
||||
}
|
||||
3
flax_model.msgpack
Normal file
3
flax_model.msgpack
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b44a67c277854fbcd96179ee8bfedb9f03f3826efc2af35f8eb9b964fd0df2b1
|
||||
size 1261979372
|
||||
8
preprocessor_config.json
Normal file
8
preprocessor_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"do_normalize": true,
|
||||
"feature_size": 1,
|
||||
"padding_side": "right",
|
||||
"padding_value": 0.0,
|
||||
"return_attention_mask": true,
|
||||
"sampling_rate": 16000
|
||||
}
|
||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a0b26f6d9d3edfde1784aef863c192a8cc1e438a23b45910ab648531ebe1857b
|
||||
size 1262142936
|
||||
1
special_tokens_map.json
Normal file
1
special_tokens_map.json
Normal file
@@ -0,0 +1 @@
|
||||
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
@@ -0,0 +1 @@
|
||||
{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "-": 5, "ء": 6, "آ": 7, "أ": 8, "ؤ": 9, "إ": 10, "ئ": 11, "ا": 12, "ب": 13, "ة": 14, "ت": 15, "ث": 16, "ج": 17, "ح": 18, "خ": 19, "د": 20, "ذ": 21, "ر": 22, "ز": 23, "س": 24, "ش": 25, "ص": 26, "ض": 27, "ط": 28, "ظ": 29, "ع": 30, "غ": 31, "ـ": 32, "ف": 33, "ق": 34, "ك": 35, "ل": 36, "م": 37, "ن": 38, "ه": 39, "و": 40, "ى": 41, "ي": 42, "ً": 43, "ٌ": 44, "ٍ": 45, "َ": 46, "ُ": 47, "ِ": 48, "ّ": 49, "ْ": 50}
|
||||
Reference in New Issue
Block a user