Duplicate from arbml/Ashaar

Co-authored-by: Zaid Alyafeai <Zaid@users.noreply.huggingface.co>

.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

.gitignore

@@ -0,0 +1,7 @@
+deep-learning-models/*
+deep-learning-models.zip
+__MACOSX/*
+__pycache__/*
+poetry_diacritizer/*
+*.pyc
+deep-learning-models.zip:Zone.Identifier

README.md

@@ -0,0 +1,14 @@
+---
+title: Ashaar
+emoji: 🧑‍🎤
+colorFrom: purple
+colorTo: blue
+sdk: gradio
+sdk_version: 3.35.2
+app_file: app.py
+pinned: false
+license: apache-2.0
+duplicated_from: arbml/Ashaar
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,151 @@
+import os
+os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' 
+import gradio as gr
+from transformers import pipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from Ashaar.utils import get_output_df, get_highlighted_patterns_html
+from Ashaar.bait_analysis import BaitAnalysis
+from langs import *
+import sys
+import json
+import argparse
+
+arg_parser = argparse.ArgumentParser()
+arg_parser.add_argument('--lang', type = str, default = 'ar')
+args = arg_parser.parse_args()
+lang = args.lang
+
+if lang == 'ar':
+    TITLE = TITLE_ar
+    DESCRIPTION = DESCRIPTION_ar
+    textbox_trg_text = textbox_trg_text_ar
+    textbox_inp_text = textbox_inp_text_ar
+    btn_trg_text = btn_trg_text_ar
+    btn_inp_text = btn_inp_text_ar
+    css = """ #textbox{ direction: RTL;}"""
+
+else:
+    TITLE = TITLE_en
+    DESCRIPTION = DESCRIPTION_en
+    textbox_trg_text = textbox_trg_text_en
+    textbox_inp_text = textbox_inp_text_en
+    btn_trg_text = btn_trg_text_en
+    btn_inp_text = btn_inp_text_en
+    css = ""
+
+gpt_tokenizer = AutoTokenizer.from_pretrained('arbml/ashaar_tokenizer')
+model = AutoModelForCausalLM.from_pretrained('arbml/Ashaar_model')
+
+theme_to_token = json.load(open("extra/theme_tokens.json", "r"))
+token_to_theme = {t:m for m,t in theme_to_token.items()}
+meter_to_token = json.load(open("extra/meter_tokens.json", "r"))
+token_to_meter = {t:m for m,t in meter_to_token.items()}
+
+analysis = BaitAnalysis()
+meter, theme, qafiyah = "", "", ""
+
+def analyze(poem):
+    global meter,theme,qafiyah, generate_btn
+    shatrs = poem.split("\n")
+    baits = [' # '.join(shatrs[2*i:2*i+2]) for i in range(len(shatrs)//2)]
+    output = analysis.analyze(baits,override_tashkeel=True)
+    meter = output['meter']
+    qafiyah = output['qafiyah'][0]
+    theme = output['theme'][-1]
+    df = get_output_df(output)
+    return get_highlighted_patterns_html(df), gr.Button.update(interactive=True)
+
+def generate(inputs, top_p = 3):
+    baits = inputs.split('\n')
+    if len(baits) % 2 !=0:
+        baits = baits[:-1]
+    poem = ' '.join(['<|bsep|> '+baits[i]+' <|vsep|> '+baits[i+1]+' </|bsep|>' for i in range(0, len(baits), 2)])
+    prompt = f"""
+    {meter_to_token[meter]} {qafiyah} {theme_to_token[theme]}
+    <|psep|>
+    {poem}
+    """.strip()
+    print(prompt)
+    encoded_input = gpt_tokenizer(prompt, return_tensors='pt')
+    output = model.generate(**encoded_input, max_length = 512, top_p = 3, do_sample=True)
+
+    result = ""
+    prev_token = ""
+    line_cnts = 0
+    for i, beam in enumerate(output[:, len(encoded_input.input_ids[0]):]):
+        if line_cnts >= 10:
+            break
+        for token in beam:
+            if line_cnts >= 10:
+                break
+            decoded = gpt_tokenizer.decode(token)
+            if 'meter' in decoded or 'theme' in decoded:
+                break
+            if decoded in ["<|vsep|>", "</|bsep|>"]:
+                result += "\n"
+                line_cnts+=1
+            elif decoded in ['<|bsep|>', '<|psep|>', '</|psep|>']:
+                pass
+            else:
+                result += decoded
+            prev_token = decoded
+        else:
+            break
+    # return theme+" "+ f"من بحر {meter} مع قافية بحر ({qafiyah})" + "\n" +result
+    return result, gr.Button.update(interactive=False)
+
+examples = [
+    [
+"""القلب أعلم يا عذول بدائه
+وأحق منك بجفنه وبمائه"""
+    ],
+    [
+"""رمتِ الفؤادَ مليحة عذراءُ
+ بسهامِ لحظٍ ما لهنَّ دواءُ"""
+    ],
+    [
+"""أذَلَّ الحِرْصُ والطَّمَعُ الرِّقابَا
+وقَد يَعفو الكَريمُ، إذا استَرَابَا"""
+    ]
+]
+
+with gr.Blocks(theme=gr.themes.Soft(), css=css) as demo:
+    with gr.Row():
+        with gr.Column():
+            gr.HTML(TITLE)
+            gr.HTML(DESCRIPTION)
+
+    with gr.Row():
+        with gr.Column():
+            textbox_output = gr.Textbox(lines=10, label=textbox_trg_text, elem_id="textbox")
+        with gr.Column():
+            inputs = gr.Textbox(lines=10, label=textbox_inp_text, elem_id="textbox")
+
+
+    with gr.Row():
+        with gr.Column():
+            if lang == 'ar':
+                trg_btn = gr.Button(btn_trg_text, interactive=False)
+            else:
+                trg_btn = gr.Button(btn_trg_text)
+
+        with gr.Column():
+            if lang == 'ar':
+                inp_btn = gr.Button(btn_inp_text)
+            else:
+                inp_btn = gr.Button(btn_inp_text, interactive = False)
+
+    with gr.Row():
+        html_output = gr.HTML()
+    
+    if lang == 'en':
+        gr.Examples(examples, textbox_output)
+        inp_btn.click(generate, inputs = textbox_output, outputs=[inputs, inp_btn])
+        trg_btn.click(analyze, inputs = textbox_output, outputs=[html_output,inp_btn])
+    else:
+        gr.Examples(examples, inputs)
+        trg_btn.click(generate, inputs = inputs, outputs=[textbox_output, trg_btn])
+        inp_btn.click(analyze, inputs = inputs, outputs=[html_output,trg_btn] )
+    
+# demo.launch(server_name = '0.0.0.0', share=True)
+demo.launch()

extra/labels.txt

@@ -0,0 +1,17 @@
+saree
+kamel
+mutakareb
+mutadarak
+munsareh
+madeed
+mujtath
+ramal
+baseet
+khafeef
+taweel
+wafer
+hazaj
+rajaz
+mudhare
+muqtadheb
+prose

extra/labels_ar.txt

@@ -0,0 +1,17 @@
+السريع
+الكامل
+المتقارب
+المتدارك
+المنسرح
+المديد
+المجتث
+الرمل
+البسيط
+الخفيف
+الطويل
+الوافر
+الهزج
+الرجز
+المضارع
+المقتضب
+النثر

extra/meter_tokens.json

@@ -0,0 +1 @@
+{"\u0627\u0644\u062e\u0641\u064a\u0641": "<|meter_0|>", "\u0627\u0644\u0645\u0636\u0627\u0631\u0639": "<|meter_1|>", "\u0627\u0644\u0645\u062c\u062a\u062b": "<|meter_2|>", "\u0627\u0644\u0631\u0645\u0644": "<|meter_3|>", "\u0627\u0644\u0628\u0633\u064a\u0637": "<|meter_4|>", "\u0627\u0644\u0645\u062a\u0642\u0627\u0631\u0628": "<|meter_5|>", "\u0627\u0644\u0648\u0627\u0641\u0631": "<|meter_6|>", "\u0627\u0644\u0645\u0642\u062a\u0636\u0628": "<|meter_7|>", "\u0627\u0644\u0645\u062f\u064a\u062f": "<|meter_8|>", "\u0627\u0644\u0646\u062b\u0631": "<|meter_9|>", "\u0627\u0644\u0647\u0632\u062c": "<|meter_10|>", "\u0627\u0644\u0645\u062a\u062f\u0627\u0631\u0643": "<|meter_11|>", "\u0627\u0644\u0645\u0646\u0633\u0631\u062d": "<|meter_12|>", "\u0627\u0644\u0637\u0648\u064a\u0644": "<|meter_13|>", "\u0627\u0644\u0643\u0627\u0645\u0644": "<|meter_14|>", "\u0627\u0644\u0631\u062c\u0632": "<|meter_15|>", "\u0627\u0644\u0633\u0631\u064a\u0639": "<|meter_16|>"}

extra/theme_tokens.json

@@ -0,0 +1 @@
+{"\u0642\u0635\u064a\u062f\u0629 \u0642\u0635\u064a\u0631\u0647": "<|theme_0|>", "\u0642\u0635\u064a\u062f\u0629 \u0645\u062f\u062d": "<|theme_1|>", "\u0642\u0635\u064a\u062f\u0629 \u0648\u0637\u0646\u064a\u0647": "<|theme_2|>", "\u0642\u0635\u064a\u062f\u0629 \u0631\u0648\u0645\u0646\u0633\u064a\u0647": "<|theme_3|>", "\u0642\u0635\u064a\u062f\u0629 \u0647\u062c\u0627\u0621": "<|theme_4|>", "\u0642\u0635\u064a\u062f\u0629 \u0627\u0639\u062a\u0630\u0627\u0631": "<|theme_5|>", "\u0642\u0635\u064a\u062f\u0629 \u0633\u064a\u0627\u0633\u064a\u0629": "<|theme_6|>", "\u0642\u0635\u064a\u062f\u0629 \u0641\u0631\u0627\u0642": "<|theme_7|>", "\u0642\u0635\u064a\u062f\u0629 \u063a\u0632\u0644": "<|theme_8|>", "\u0642\u0635\u064a\u062f\u0629 \u0630\u0645": "<|theme_9|>", "\u0642\u0635\u064a\u062f\u0629 \u0631\u062b\u0627\u0621": "<|theme_10|>", "null": "<|theme_11|>", "\u0642\u0635\u064a\u062f\u0629 \u0634\u0648\u0642": "<|theme_12|>", "\u0642\u0635\u064a\u062f\u0629 \u0627\u0644\u0645\u0639\u0644\u0642\u0627\u062a": "<|theme_13|>", "\u0642\u0635\u064a\u062f\u0629 \u0627\u0644\u0627\u0646\u0627\u0634\u064a\u062f": "<|theme_14|>", "\u0642\u0635\u064a\u062f\u0629 \u062d\u0632\u064a\u0646\u0647": "<|theme_15|>", "\u0642\u0635\u064a\u062f\u0629 \u0639\u062a\u0627\u0628": "<|theme_16|>", "\u0642\u0635\u064a\u062f\u0629 \u0639\u0627\u0645\u0647": "<|theme_17|>", "\u0642\u0635\u064a\u062f\u0629 \u062f\u064a\u0646\u064a\u0629": "<|theme_18|>"}

langs.py

@@ -0,0 +1,59 @@
+IMG = """<p align = 'center'>
+<img src='https://raw.githubusercontent.com/ARBML/Ashaar/master/images/ashaar_icon.png' width='150px' alt='logo for Ashaar'/>
+</p>
+
+"""
+TITLE_ar="""<h1 style="font-size: 30px;" align="center">أَشْعــَـار: تحليل وإنشاء الشعر العربي</h1>"""
+DESCRIPTION_ar = IMG
+
+DESCRIPTION_ar +=""" <p dir='rtl'>
+هذا البرنامج يتيح للمستخدم تحليل وإنشاء الشعر العربي.
+لإنشاء الشعر العربي تم تدريب نموج يقوم بإستخدام البحر والقافية والعاطفة لإنشاء أكمال للقصيدة بناء على هذه الشروط.
+بالإضافة إلى نموذج إنشاء الشعر يحتوي البرنامج على نماذج لتصنيف الحقبة الزمنية والعاطفة والبحر و كذلك تشكيل الشعر .
+يقوم البرنامج بإستخدام هذه النماذج لإيجاد الخلل في القصيدة من خلال إضافة ألوان معينة تدل على اماكن الخلل.
+لإستخدام البرنامج قم في البداية بكتابة قصيدة تحتوي على عدد زوجي من الأبيات و من ثم قم بالضغط على تحليل ، وبعد إنتهاء التحليل بالإمكان إنشاء إكمال للقصيدة.
+عند الضغط على زر التحليل يتم إنشاء جدول التحليل الذي يشرح العديد من الأشياء :
+</p>
+"""
+DESCRIPTION_ar+= """<div dir='RTL'>
+<ul>
+  <li> المشكل : تشكيل كل شطر من القصيدة المدخلة</li>
+  <li>الكتابة العروضية: وتقوم هذه الكتابة على التعبير عن كل منطوق في اللغة وتبيانه حتى لو لم يكن يكتب إملائياً
+ </li>
+  <li>التفعيلة: تفعيلات القصيدة ، مثالاً : طَويلٌ لَهُ دُونَ البُحورِ فضائل فَعُوْلُنْ مَفَاْعِيْلُنْ فَعُوْلُنْ مَفَاْعِلُ
+ </li>
+  <li>النمط: يحدد حركة وسكون كل حرف في الكتابة العروضية. نستخدم الألوان التالية للرمز إلى خلل في الكتابة العروضية: الأحمر: حرف محذوف، الأزرق: حرف مضاف، الأصفر: حركة مقلوبة.</li>
+</ul>
+</div>
+"""
+DESCRIPTION_ar+= """<p dir='rtl'>
+قمنا بتوفير الشفرة البرمجية كلها على 
+<a href ='https://github.com/ARBML/Ashaar'> GitHub</a>.
+</p>
+"""
+
+TITLE_en="""<h1 style="font-size: 30px;" align="center">Ashaar: Arabic Poetry Analysis and Generation</h1>"""
+DESCRIPTION_en = IMG
+
+DESCRIPTION_en +="""
+The demo provides a way to generate analysis for poetry and also complete the poetry. 
+The generative model is a character-based conditional GPT-2 model. The pipeline contains many models for 
+classification, diacritization and conditional generation. Check our <a src='https://github.com/ARBML/Ashaar'>GitHub</a> for more techincal details
+about this work. In the demo we have two basic pipelines. Analyze which predicts the meter, era, theme, diacritized text, qafiyah and, arudi style.
+The other module, Generate which takes the input text, meter, theme and qafiyah to generate the full poem. 
+"""
+
+btn_trg_text_ar = "إنشاء"
+btn_inp_text_ar = "تحليل"
+
+btn_inp_text_en = "Generate"
+btn_trg_text_en = "Analyze"
+
+textbox_inp_text_ar = "القصيدة المدخلة"
+textbox_trg_text_ar = "القصيدة المنشئة"
+
+textbox_trg_text_en = "Input Poem"
+textbox_inp_text_en = "Generated Poem"
+
+
+

poetry_diacritizer/__init__.py

@@ -0,0 +1 @@
+from poetry_diacritizer import predict

poetry_diacritizer/config/ashaar.yml

@@ -0,0 +1,52 @@
+session_name: base
+
+data_directory: "data"
+data_type: "ashaar_proc"
+log_directory: "log_dir_ashaar"
+load_training_data: true
+load_test_data: false
+load_validation_data: true
+n_training_examples: null # null load all training examples, good for fast loading
+n_test_examples: null  # null load all test examples
+n_validation_examples: null # null load all validation examples
+test_file_name: "test.csv"
+is_data_preprocessed: false # The data file is organized as (original text | text | diacritics)
+data_separator: '|' # Required if the data already processed
+diacritics_separator: '*'  # Required if the data already processed
+text_encoder: ArabicEncoderWithStartSymbol
+text_cleaner: valid_arabic_cleaners # a white list that uses only Arabic letters, punctuations, and a space
+max_len: 600 # sentences larger than this size will not be used
+max_sen_len: null
+
+max_steps: 10000
+learning_rate: 0.001
+batch_size: 32
+adam_beta1: 0.9
+adam_beta2: 0.999
+use_decay: true
+weight_decay: 0.0
+embedding_dim: 256
+use_prenet: false
+prenet_sizes: [512, 256]
+cbhg_projections: [128, 256]
+cbhg_filters: 16
+cbhg_gru_units: 256
+post_cbhg_layers_units: [256, 256]
+post_cbhg_use_batch_norm: true
+
+use_mixed_precision: false
+optimizer_type: Adam
+device: cuda
+
+# LOGGING
+evaluate_frequency: 50000000
+max_eval_batches: 100
+evaluate_with_error_rates_frequency: 1000
+n_predicted_text_tensorboard: 10 # To be written to the tensorboard
+model_save_frequency: 1000
+train_plotting_frequency: 50000000 # No plotting for this model
+n_steps_avg_losses: [100, 500, 1_000, 5_000] # command line display of average loss values for the last n steps
+error_rates_n_batches: 10000 # if calculating error rate is slow, then you can specify the number of batches to be calculated
+
+test_model_path: null # load the last saved model
+train_resume_model_path: null # load last saved model

poetry_diacritizer/config/baseline.yml

@@ -0,0 +1,47 @@
+session_name: base
+
+data_directory: "data"
+data_type: "CA_MSA"
+log_directory: "log_dir"
+load_training_data: true
+load_test_data: false
+load_validation_data: true
+n_training_examples: null # null load all training examples, good for fast loading
+n_test_examples: null  # null load all test examples
+n_validation_examples: null # null load all validation examples
+test_file_name: "test.csv"
+is_data_preprocessed: false # The data file is organized as (original text | text | diacritics)
+data_separator: '|' # Required if the data already processed
+diacritics_separator: '*'  # Required if the data already processed
+text_encoder: ArabicEncoderWithStartSymbol
+text_cleaner: valid_arabic_cleaners # a white list that uses only Arabic letters, punctuations, and a space
+max_len: 600 # sentences larger than this size will not be used
+
+
+max_steps: 2_000_000
+learning_rate: 0.001
+batch_size: 64
+adam_beta1: 0.9
+adam_beta2: 0.999
+use_decay: true
+weight_decay: 0.0
+embedding_dim: 512
+n_layers: 3
+layers_units: [256, 256, 256]
+use_mixed_precision: false
+optimizer_type: Adam
+use_batch_norm: False
+device: cuda
+max_sen_len: 256
+
+# LOGGING
+evaluate_frequency: 5000
+evaluate_with_error_rates_frequency: 5000
+n_predicted_text_tensorboard: 10 # To be written to the tensorboard
+model_save_frequency: 5000
+train_plotting_frequency: 50000000 # No plotting for this model
+n_steps_avg_losses: [100, 500, 1_000, 5_000] # command line display of average loss values for the last n steps
+error_rates_n_batches: 10000 # if calculating error rate is slow, then you can specify the number of batches to be calculated
+
+test_model_path: null # load the last saved model
+train_resume_model_path: null # load last saved model

poetry_diacritizer/config/cbhg.yml

@@ -0,0 +1,52 @@
+session_name: base
+
+data_directory: "data"
+data_type: "CA_MSA"
+log_directory: "log_dir_cbhg"
+load_training_data: true
+load_test_data: false
+load_validation_data: true
+n_training_examples: null # null load all training examples, good for fast loading
+n_test_examples: null  # null load all test examples
+n_validation_examples: null # null load all validation examples
+test_file_name: "test.csv"
+is_data_preprocessed: false # The data file is organized as (original text | text | diacritics)
+data_separator: '|' # Required if the data already processed
+diacritics_separator: '*'  # Required if the data already processed
+text_encoder: ArabicEncoderWithStartSymbol
+text_cleaner: valid_arabic_cleaners # a white list that uses only Arabic letters, punctuations, and a space
+max_len: 600 # sentences larger than this size will not be used
+max_sen_len: null
+
+max_steps: 5000
+learning_rate: 0.001
+batch_size: 32
+adam_beta1: 0.9
+adam_beta2: 0.999
+use_decay: true
+weight_decay: 0.0
+embedding_dim: 256
+use_prenet: false
+prenet_sizes: [512, 256]
+cbhg_projections: [128, 256]
+cbhg_filters: 16
+cbhg_gru_units: 256
+post_cbhg_layers_units: [256, 256]
+post_cbhg_use_batch_norm: true
+
+use_mixed_precision: false
+optimizer_type: Adam
+device: cuda
+
+# LOGGING
+evaluate_frequency: 50000000
+max_eval_batches: 100
+evaluate_with_error_rates_frequency: 1000
+n_predicted_text_tensorboard: 10 # To be written to the tensorboard
+model_save_frequency: 5000
+train_plotting_frequency: 50000000 # No plotting for this model
+n_steps_avg_losses: [100, 500, 1_000, 5_000] # command line display of average loss values for the last n steps
+error_rates_n_batches: 10000 # if calculating error rate is slow, then you can specify the number of batches to be calculated
+
+test_model_path: null # load the last saved model
+train_resume_model_path: null # load last saved model

poetry_diacritizer/config/cbhg2.yml

@@ -0,0 +1,51 @@
+session_name: base
+
+data_directory: "ashaar"
+data_type: "CA_MSA"
+log_directory: "/content/drive/MyDrive/Research/Barmajan/Diacritization/log_ashaar_dir"
+load_training_data: true
+load_test_data: false
+load_validation_data: true
+n_training_examples: null # null load all training examples, good for fast loading
+n_test_examples: null  # null load all test examples
+n_validation_examples: null # null load all validation examples
+test_file_name: "test.csv"
+is_data_preprocessed: false # The data file is organized as (original text | text | diacritics)
+data_separator: '|' # Required if the data already processed
+diacritics_separator: '*'  # Required if the data already processed
+text_encoder: ArabicEncoderWithStartSymbol
+text_cleaner: valid_arabic_cleaners # a white list that uses only Arabic letters, punctuations, and a space
+max_len: 600 # sentences larger than this size will not be used
+
+
+max_steps: 25_000
+learning_rate: 0.001
+batch_size: 32
+adam_beta1: 0.9
+adam_beta2: 0.999
+use_decay: true
+weight_decay: 0.0
+embedding_dim: 256
+use_prenet: false
+prenet_sizes: [512, 256]
+cbhg_projections: [128, 256]
+cbhg_filters: 16
+cbhg_gru_units: 256
+post_cbhg_layers_units: [256, 256]
+post_cbhg_use_batch_norm: true
+
+use_mixed_precision: false
+optimizer_type: Adam
+device: cuda
+
+# LOGGING
+evaluate_frequency: 1000
+evaluate_with_error_rates_frequency: 1000
+n_predicted_text_tensorboard: 10 # To be written to the tensorboard
+model_save_frequency: 1000
+train_plotting_frequency: 50000000 # No plotting for this model
+n_steps_avg_losses: [100, 500, 1_000, 5_000] # command line display of average loss values for the last n steps
+error_rates_n_batches: 10000 # if calculating error rate is slow, then you can specify the number of batches to be calculated
+
+test_model_path: null # load the last saved model
+train_resume_model_path: "/content/drive/MyDrive/Research/Barmajan/Diacritization/log_cleaned_dir/CA_MSA.base.cbhg/models/20000-snapshot.pt" # load last saved model

poetry_diacritizer/config/gpt-0.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_0
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 0
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: true
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-1.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_1
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 1
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: true
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-2.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_2
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 2
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: true
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-3.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_3
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 3
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: true
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-4.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_4
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 4
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: true
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-5.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_5
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 5
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: true
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-6.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_6
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 6
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: true
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-7.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_7
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 7
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: true
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-8.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_8
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 8
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: true
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-9.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_9
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 9
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: true
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-0-tash-proc.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: tash_proc
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_0_tash_proc
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 0
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-0-test.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_0_test
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 0
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-0.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_0
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 0
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-1-tash-proc.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: tash_proc
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_1_tash_proc
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 1
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-1.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_1
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 1
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-2-tash-proc.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: tash_proc
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_2_tash_proc
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 2
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-2.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_2
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 2
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-3-tash-proc.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: tash_proc
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_3_tash_proc
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 3
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-3.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_3
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 3
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-4-tash-proc.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: tash_proc
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_4_tash_proc
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 4
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-4.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_4
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 4
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-5-tash-proc.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: tash_proc
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_5_tash_proc
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 5
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-5-test.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: logs/log_dir_cls_5_test
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 5
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-5.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_5
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 5
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-6-tash-proc.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: tash_proc
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_6_tash_proc
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 6
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-6.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_6
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 6
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-7-tash-proc.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: tash_proc
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_7_tash_proc
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 7
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-7.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_7
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 7
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-8-tash-proc.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: tash_proc
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_8_tash_proc
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 8
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-8.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_8
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 8
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-9-tash-proc.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: tash_proc
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_9_tash_proc
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 9
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-9-test.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: logs/log_dir_cls_9_test
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 9
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-9.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_9
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 9
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-cls-tash-proc.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: tash_proc
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_cls_0_test
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 5000
+model_save_frequency: 5000
+n_layer: 0
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: false
+use_mixed_precision: false
+weight_decay: 0.0

poetry_diacritizer/config/gpt-lstm-0-50K.yml

@@ -0,0 +1,46 @@
+adam_beta1: 0.9
+adam_beta2: 0.999
+base_model_path: ashaar-from-scratch-with-spaces-no-tatweel-epochs-75
+batch_size: 64
+data_directory: data
+data_separator: '|'
+data_type: CA_MSA
+device: cuda
+diacritics_separator: '*'
+error_rates_n_batches: 10000
+evaluate_frequency: 50000000
+evaluate_with_error_rates_frequency: 1000
+freeze: true
+is_data_preprocessed: false
+learning_rate: 0.001
+load_test_data: false
+load_training_data: true
+load_validation_data: true
+log_directory: log_dir_lstm_0_50K
+max_eval_batches: -1
+max_len: 600
+max_sen_len: 256
+max_steps: 50000
+model_save_frequency: 5000
+n_layer: 0
+n_predicted_text_tensorboard: 10
+n_steps_avg_losses:
+- 100
+- 500
+- 1000
+- 5000
+n_test_examples: null
+n_training_examples: null
+n_validation_examples: null
+optimizer_type: Adam
+session_name: base
+test_file_name: test.csv
+test_model_path: null
+text_cleaner: valid_arabic_cleaners
+text_encoder: ArabicEncoderWithStartSymbol
+train_plotting_frequency: 50000000
+train_resume_model_path: null
+use_decay: true
+use_lstm: true
+use_mixed_precision: false
+weight_decay: 0.0