Translation
Transformers
Safetensors
English
Arabic
marian
text2text-generation
Omar-youssef commited on
Commit
8a3be92
·
verified ·
1 Parent(s): c66ffa1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +92 -139
README.md CHANGED
@@ -1,199 +1,152 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
 
 
 
 
 
 
 
 
4
  ---
5
 
6
- # Model Card for Model ID
7
-
8
- <!-- Provide a quick summary of what the model is/does. -->
9
-
10
 
 
11
 
12
  ## Model Details
13
 
14
  ### Model Description
15
 
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
-
28
- ### Model Sources [optional]
29
-
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
-
36
- ## Uses
37
-
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
- ### Direct Use
41
-
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
 
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
 
 
 
 
 
49
 
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
 
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
 
56
- [More Information Needed]
 
57
 
58
- ## Bias, Risks, and Limitations
 
59
 
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
 
 
61
 
62
- [More Information Needed]
 
63
 
64
- ### Recommendations
 
 
65
 
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
 
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
 
70
- ## How to Get Started with the Model
 
 
 
 
 
71
 
72
- Use the code below to get started with the model.
73
 
74
- [More Information Needed]
75
 
76
  ## Training Details
77
 
78
  ### Training Data
79
 
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
 
82
- [More Information Needed]
 
 
 
83
 
84
  ### Training Procedure
85
 
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
  #### Training Hyperparameters
94
 
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
 
 
 
 
100
 
101
- [More Information Needed]
102
 
103
  ## Evaluation
104
 
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
 
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
-
115
- #### Factors
116
-
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
-
121
- #### Metrics
122
-
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
126
 
127
  ### Results
128
 
129
- [More Information Needed]
130
-
131
- #### Summary
132
 
 
133
 
 
134
 
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
 
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
 
153
- ## Technical Specifications [optional]
154
 
155
- ### Model Architecture and Objective
156
 
157
- [More Information Needed]
 
 
 
158
 
159
  ### Compute Infrastructure
160
 
161
- [More Information Needed]
 
 
162
 
163
- #### Hardware
164
-
165
- [More Information Needed]
166
-
167
- #### Software
168
-
169
- [More Information Needed]
170
-
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
-
175
- **BibTeX:**
176
-
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
184
-
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
-
187
- [More Information Needed]
188
 
189
- ## More Information [optional]
190
 
191
- [More Information Needed]
192
 
193
- ## Model Card Authors [optional]
 
 
 
 
 
 
 
 
194
 
195
- [More Information Needed]
196
 
197
  ## Model Card Contact
198
 
199
- [More Information Needed]
 
1
  ---
2
  library_name: transformers
3
+ license: apache-2.0
4
+ datasets:
5
+ - Omar-youssef/English-Egyptian-Arabic-Translation-Pairs
6
+ language:
7
+ - en
8
+ - ar
9
+ metrics:
10
+ - bleu
11
+ base_model:
12
+ - Helsinki-NLP/opus-mt-tc-big-en-ar
13
+ pipeline_tag: translation
14
  ---
15
 
16
+ # English Egyptian Arabic Translation Model
 
 
 
17
 
18
+ A fine-tuned version of [Helsinki-NLP/opus-mt-tc-big-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-ar) specialized for **Egyptian Arabic dialect** translation.
19
 
20
  ## Model Details
21
 
22
  ### Model Description
23
 
24
+ This model translates English text into **Egyptian Arabic (العامية المصرية)**, the most widely spoken Arabic dialect. It was fine-tuned on Egyptian Arabic translation pairs, making it more accurate for colloquial Egyptian Arabic compared to the base model which targets Modern Standard Arabic (MSA).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
 
26
+ - **Developed by:** Omar Youssef
27
+ - **Model type:** Seq2Seq Translation (MarianMT)
28
+ - **Language(s):** English (`en`) → Egyptian Arabic (`ar`)
29
+ - **License:** Apache 2.0
30
+ - **Base model:** [Helsinki-NLP/opus-mt-tc-big-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-en-ar)
31
+ - **Fine-tuned on:** [Omar-youssef/English-Egyptian-Arabic-Translation-Pairs](https://huggingface.co/datasets/Omar-youssef/English-Egyptian-Arabic-Translation-Pairs)
32
 
33
+ ---
 
 
34
 
35
+ ## How to Get Started
36
 
37
+ ```python
38
+ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
39
 
40
+ tokenizer = AutoTokenizer.from_pretrained("Omar-youssef/english-egyptian-arabic-translation-v1")
41
+ model = AutoModelForSeq2SeqLM.from_pretrained("Omar-youssef/english-egyptian-arabic-translation-v1")
42
 
43
+ def translate(text):
44
+ inputs = tokenizer.encode(text, return_tensors="pt")
45
+ outputs = model.generate(inputs, max_length=128, num_beams=4, early_stopping=True)
46
+ return tokenizer.decode(outputs[0], skip_special_tokens=True)
47
 
48
+ print(translate("A novel is a long prose narrative that usually describes fictional characters and events in the form of a sequential story."))
49
+ # Output: الرواية هي رواية نثرية طويلة عادةً بتصف شخصيات وأحداث خيالية في شكل قصة متتابعة.
50
 
51
+ print(translate("The rapid advancement of artificial intelligence is transforming many industries, creating new opportunities while also raising important ethical and social concerns."))
52
+ # Output: التقدم السريع للـ Artificial Intelligence بيغير صناعات كتير، وبيخلق فرص جديدة وفي نفس الوقت بيثير اهتمامات أخلاقية واجتماعية مهمة.
53
+ ```
54
 
55
+ ---
56
 
57
+ ## Uses
58
 
59
+ ### Direct Use
60
+ Translate English sentences or short paragraphs into Egyptian Arabic dialect. Suitable for:
61
+ - Chatbots targeting Egyptian Arabic speakers
62
+ - Language learning applications
63
+ - Content localization for Egyptian audiences
64
+ - Research on Arabic dialect translation
65
 
 
66
 
67
+ ---
68
 
69
  ## Training Details
70
 
71
  ### Training Data
72
 
73
+ Fine-tuned exclusively on the **Egyptian Arabic** [Omar-youssef/English-Egyptian-Arabic-Translation-Pairs](https://huggingface.co/datasets/Omar-youssef/English-Egyptian-Arabic-Translation-Pairs) dataset.
74
 
75
+ - **Language filter:** `Egyptian Arabic` only
76
+ - **Split:** 80% train / 20% test (`seed=42`)
77
+ - **Source language:** English
78
+ - **Target language:** Egyptian Arabic
79
 
80
  ### Training Procedure
81
 
 
 
 
 
 
 
 
82
  #### Training Hyperparameters
83
 
84
+ - **Learning rate:** 5e-5
85
+ - **Batch size:** 16 (per device)
86
+ - **Gradient accumulation steps:** 2 (effective batch size = 32)
87
+ - **Epochs:** 3
88
+ - **Warmup steps:** 500
89
+ - **Weight decay:** 0.01
90
+ - **Optimizer:** AdamW
91
+ - **Evaluation strategy:** steps (every 50 steps)
92
+ - **Best model selection:** highest BLEU score on validation set
93
 
94
+ ---
95
 
96
  ## Evaluation
97
 
98
+ ### Metrics
 
 
 
 
99
 
100
+ | Metric | Description | Range | Better When |
101
+ |--------|-------------|-------|-------------|
102
+ | **BLEU** | N-gram overlap between predictions and references | 0 → 1 | Higher ↑ |
 
 
 
 
 
 
 
 
 
 
 
 
103
 
104
  ### Results
105
 
106
+ | Metric | Score |
107
+ |--------|-------|
108
+ | **BLEU** | **0.6985** |
109
 
110
+ > BLEU of **0.6985** (69.85%) indicates high-quality translations with strong overlap against Egyptian Arabic references.
111
 
112
+ ---
113
 
 
 
 
 
 
 
 
 
 
 
 
114
 
115
+ ---
 
 
 
 
116
 
117
+ ## Technical Specifications
118
 
119
+ ### Model Architecture
120
 
121
+ - **Architecture:** MarianMT (Encoder-Decoder Transformer)
122
+ - **Base:** Helsinki-NLP/opus-mt-tc-big-en-ar
123
+ - **Parameters:** ~600M
124
+ - **Task:** Sequence-to-Sequence Translation
125
 
126
  ### Compute Infrastructure
127
 
128
+ - **Hardware:** Kaggle GPU (T4 )
129
+ - **Framework:** Hugging Face Transformers
130
+ - **Training time:** ~30-60 minutes
131
 
132
+ ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
133
 
134
+ ## Citation
135
 
136
+ If you use this model, please cite the base model and dataset:
137
 
138
+ ```bibtex
139
+ @misc{omar-youssef-egyptian-translation,
140
+ author = {Omar Youssef},
141
+ title = {English to Egyptian Arabic Translation Model},
142
+ year = {2024},
143
+ publisher = {Hugging Face},
144
+ url = {https://huggingface.co/Omar-youssef/english-egyptian-arabic-translation-v1}
145
+ }
146
+ ```
147
 
148
+ ---
149
 
150
  ## Model Card Contact
151
 
152
+ For questions or feedback, open a discussion on this model's [Hugging Face page](https://huggingface.co/Omar-youssef/english-egyptian-arabic-translation-v1/discussions).