初始化项目，由ModelHub XC社区提供模型

Model: IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53 Source: Original Platform
2026-05-08 11:40:38 +08:00
commit 3470c2e74a
10 changed files with 476 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,215 @@
+---
+license: apache-2.0
+language:
+- ar
+- arz
+library_name: transformers
+pipeline_tag: automatic-speech-recognition
+datasets:
+- YouTube
+- rsalshalan/MGB3
+- pain/MASC
+- mozilla-foundation/common_voice_15_0
+- halabi2016/arabic_speech_corpus
+model-index:
+- name: egyptian-arabic-wav2vec2-xlsr-53
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: mozilla-foundation/common_voice_17_0
+      type: mozilla-foundation/common_voice_17_0
+      args: ar
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 27.20
+base_model:
+- omarxadel/wav2vec2-large-xlsr-53-arabic-egyptian
+---
+
+# 🐪🇪🇬 Egyptian Arabic ASR — wav2vec2-large-xlsr-53 Fine-tuned
+
+This model is a fine-tuned version of [omarxadel/wav2vec2-large-xlsr-53-arabic-egyptian](https://huggingface.co/omarxadel/wav2vec2-large-xlsr-53-arabic-egyptian), 
+enhancing **Egyptian Arabic**, **Modern Standard Arabic (MSA)** and **Gulf / Levantine Arabic** for Automatic Speech Recognition.
+
+---
+
+## 📚 Dataset
+
+It was trained on a diverse combination of publicly available and custom-collected Arabic speech datasets, including:
+
+- **📺 YouTube Egyptian Arabic Speech** *(custom-curated)*
+- **🎧 MASC** *(Media Arabic Speech Corpus)*
+- **🌍 Common Voice 15 - Arabic**
+- **📻 MGB-3 Broadcast Speech**
+- **🗂️ Arabic Speech Corpus**
+
+---
+
+## 🔥 Model Highlights
+
+- 📌 Focused on real-life Egyptian Arabic speech (YouTube, spontaneous, conversational)
+- 🚀 Supports MSA and other Arabic dialects.
+- 🔉 Trained on both scripted and natural speech
+
+---
+
+## 💬 Languages & Dialects
+
+| Dialect                      | Coverage     |
+| ---------------------------- | ------------ |
+| Egyptian Arabic              | ✅ Primary   |
+| Modern Standard Arabic (MSA) | ✅ Supported |
+| Gulf / Levantine             | ✅ Supported |
+
+---
+
+## 🚀 Usage
+
+```python
+from transformers import pipeline
+
+asr = pipeline("automatic-speech-recognition", model="IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53")
+asr("path/to/audio.wav")
+
+# Long-Form Transcription: https://huggingface.co/blog/asr-chunking
+asr = pipeline("automatic-speech-recognition", model="IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53", chunk_length_s=30) 
+asr("path/to/audio.wav")
+```
+
+```python
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+import torch
+import torchaudio
+
+model = Wav2Vec2ForCTC.from_pretrained("IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53")
+processor = Wav2Vec2Processor.from_pretrained("IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53")
+
+# Load audio (must be mono, 16kHz)
+waveform, sr = torchaudio.load("path/to/audio.wav")
+
+# Convert to mono if not already
+if waveform.shape[0] > 1:
+    waveform = torch.mean(waveform, dim=0, keepdim=True)
+
+# Resample if needed to 16 kHz
+if sr != 16000:
+    resampler = torchaudio.transforms.Resample(orig_freq=sr, new_freq=16000)
+    waveform = resampler(waveform)
+
+inputs = processor(waveform.squeeze(), sampling_rate=16000, return_tensors="pt")
+
+with torch.inference_mode():
+    logits = model(**inputs).logits
+
+predicted_ids = torch.argmax(logits, dim=-1)
+transcription = processor.batch_decode(predicted_ids)
+print(transcription)
+```
+
+---
+
+## 🧪 Evaluation
+
+```python
+import torch
+import torchaudio
+import re
+from datasets import load_dataset
+from evaluate import load
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+
+# Device setup
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+
+# 🔑 Replace with your Hugging Face token and the desired Wav2Vec2-based model ID
+HF_TOKEN = "your_hf_token"
+MODEL_NAME = "your_model_name_or_path"
+
+# Load the Common Voice 17.0 Arabic test split
+test_dataset = load_dataset(
+    "mozilla-foundation/common_voice_17_0", 
+    "ar", 
+    split="test", 
+    token=HF_TOKEN
+)
+
+# Load WER metric
+wer = load("wer")
+
+# Load processor and model
+processor = Wav2Vec2Processor.from_pretrained(MODEL_NAME, token=HF_TOKEN)
+model = Wav2Vec2ForCTC.from_pretrained(MODEL_NAME, token=HF_TOKEN).to(device)
+
+# Define regex for cleaning up unwanted characters
+CHARS_TO_IGNORE_REGEX = r'[\؛\—\_get\«\»\ـ\,\?\.\!\-\;\:"\“\%\‘\”\<5C>\#\،\☭,\؟]'
+
+def preprocess(batch):
+    """Removes unwanted characters and resamples audio to 16kHz."""
+    batch["sentence"] = re.sub(CHARS_TO_IGNORE_REGEX, "", batch["sentence"])
+    speech_array, sampling_rate = torchaudio.load(batch["path"])
+    resampler = torchaudio.transforms.Resample(orig_freq=sampling_rate, new_freq=16_000)
+    batch["speech"] = resampler(speech_array).squeeze().numpy()
+    return batch
+
+# Apply preprocessing
+test_dataset = test_dataset.map(preprocess)
+
+def predict(batch):
+    """Runs inference and decodes predicted text."""
+    inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+    
+    with torch.inference_mode():
+        logits = model(
+            input_values=inputs["input_values"].to(device), 
+            attention_mask=inputs["attention_mask"].to(device)
+        ).logits
+
+    predicted_ids = torch.argmax(logits, dim=-1)
+    batch["pred_strings"] = processor.batch_decode(predicted_ids)
+    return batch
+
+# Run prediction
+result = test_dataset.map(predict, batched=True, batch_size=8)
+
+# Compute and print Word Error Rate
+wer_score = wer.compute(predictions=result["pred_strings"], references=result["sentence"])
+print(f"WER: {wer_score * 100:.2f}%")
+```
+
+---
+
+## 🗣️ Model Comparison on Common Voice 17.0 Arabic Subset (Test Set)
+
+| **Model**                                          | **WER (%)** |
+| -------------------------------------------------- | ----------: |
+| **`IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53`** |   **27.20** |
+| `jonatasgrosman/wav2vec2-large-xlsr-53-arabic`     |       45.55 |
+| `AndrewMcDowell/wav2vec2-xls-r-300m-arabic`        |       47.22 |
+| `openai/whisper-large-v3`*                         |       52.36 |
+| `Ahmed107/hamsa-v0.6Q`*                            |       53.27 |
+| `nadsoft/hamsa-v0.1-beta`*                         |       65.60 |
+| `openai/whisper-medium`*                           |       67.75 |
+| `openai/whisper-small`*                            |       74.16 |
+| `omarxadel/wav2vec2-large-xlsr-53-arabic-egyptian` |       91.82 |
+| `arbml/wav2vec2-large-xlsr-53-arabic-egyptian`     |       93.92 |
+| `mboushaba/whisper-large-v3-turbo-arabic`*         |       96.90 |
+
+\*: *Whisper models were decoded using beam search (`beam_size = 5`) and evaluated using `BasicTextNormalizer` with `remove_diacritics=False` and `split_letters=False`, applied to both predictions and reference text.*
+
+---
+
+## ✨ Citation
+
+If you want to cite this model you can use this:
+
+```bibtex
+@misc{amin2025egyptianasr,
+  title={Egyptian Arabic ASR with wav2vec2 XLSR 53},
+  author={Ibrahim Amin},
+  year={2025},
+  howpublished={\url{https://huggingface.co/IbrahimAmin/egyptian-arabic-wav2vec2-xlsr-53}},
+}
+```
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,4 @@
+{
+  "</s>": 42,
+  "<s>": 41
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "omarxadel/wav2vec2-large-xlsr-53-arabic-egyptian",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "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,
+  "diversity_loss_weight": 0.1,
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.0,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 40,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 43,
+  "xvector_output_dim": 512
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d694bc610f9850d3ea4a1ef5de8fb27c49c333c015545715972b36f2432824
+size 1261979588
--- a/preprocessor_config.json
+++ b/preprocessor_config.json
@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "39": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "42": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3410c18d918bbb020b7fed2ecde45e0536684b0ff5c712d0c8b289181dc6824c
+size 4728
--- a/vocab.json
+++ b/vocab.json
@@ -0,0 +1,43 @@
+{
+  "[PAD]": 40,
+  "[UNK]": 39,
+  "|": 0,
+  "ء": 1,
+  "آ": 2,
+  "أ": 3,
+  "إ": 4,
+  "ئ": 5,
+  "ا": 6,
+  "ب": 7,
+  "ة": 8,
+  "ت": 9,
+  "ث": 10,
+  "ج": 11,
+  "ح": 12,
+  "خ": 13,
+  "د": 14,
+  "ذ": 15,
+  "ر": 16,
+  "ز": 17,
+  "س": 18,
+  "ش": 19,
+  "ص": 20,
+  "ض": 21,
+  "ط": 22,
+  "ظ": 23,
+  "ع": 24,
+  "غ": 25,
+  "ف": 26,
+  "ق": 27,
+  "ك": 28,
+  "ل": 29,
+  "م": 30,
+  "ن": 31,
+  "ه": 32,
+  "و": 33,
+  "ى": 34,
+  "ي": 35,
+  "ڨ": 36,
+  "ی": 37,
+  "ﻻ": 38
+}