---
language: zgh
language_name: Standard Moroccan Tamazight
language_family: berber
tags:
  - wikilangs
  - nlp
  - tokenizer
  - embeddings
  - n-gram
  - markov
  - wikipedia
  - feature-extraction
  - sentence-similarity
  - tokenization
  - n-grams
  - markov-chain
  - text-mining
  - fasttext
  - babelvec
  - vocabulous
  - vocabulary
  - monolingual
  - family-berber
license: mit
library_name: wikilangs
pipeline_tag: text-generation
datasets:
  - omarkamali/wikipedia-monthly
dataset_info:
  name: wikipedia-monthly
  description: Monthly snapshots of Wikipedia articles across 300+ languages
metrics:
  - name: best_compression_ratio
    type: compression
    value: 3.844
  - name: best_isotropy
    type: isotropy
    value: 0.7259
  - name: vocabulary_size
    type: vocab
    value: 0
generated: 2026-01-11
---

# Standard Moroccan Tamazight - Wikilangs Models
## Comprehensive Research Report & Full Ablation Study

This repository contains NLP models trained and evaluated by Wikilangs, specifically on **Standard Moroccan Tamazight** Wikipedia data.
We analyze tokenizers, n-gram models, Markov chains, vocabulary statistics, and word embeddings.

## 📋 Repository Contents

### Models & Assets

- Tokenizers (8k, 16k, 32k, 64k)
- N-gram models (2, 3, 4, 5-gram)
- Markov chains (context of 1, 2, 3, 4 and 5)
- Subword N-gram and Markov chains
- Embeddings in various sizes and dimensions (aligned and unaligned)
- Language Vocabulary
- Language Statistics

![Performance Dashboard](visualizations/performance_dashboard.png)

### Analysis and Evaluation

- [1. Tokenizer Evaluation](#1-tokenizer-evaluation)
- [2. N-gram Model Evaluation](#2-n-gram-model-evaluation)
- [3. Markov Chain Evaluation](#3-markov-chain-evaluation)
- [4. Vocabulary Analysis](#4-vocabulary-analysis)
- [5. Word Embeddings Evaluation](#5-word-embeddings-evaluation)
- [6. Morphological Analysis (Experimental)](#6--morphological-analysis-experimental)
- [7. Summary & Recommendations](#7-summary--recommendations)
- [Metrics Glossary](#appendix-metrics-glossary--interpretation-guide)
- [Visualizations Index](#visualizations-index)

---
## 1. Tokenizer Evaluation

![Tokenizer Compression](visualizations/tokenizer_compression.png)

![Tokenizer Fertility](visualizations/tokenizer_fertility.png)

![Tokenizer OOV](visualizations/tokenizer_oov.png)

![Total Tokens](visualizations/tokenizer_total_tokens.png)

### Results

| Vocab Size | Compression | Avg Token Len | UNK Rate | Total Tokens |
|------------|-------------|---------------|----------|--------------|
| **8k** | 3.062x | 3.07 | 0.9549% | 377,124 |
| **16k** | 3.360x | 3.36 | 1.0478% | 343,658 |
| **32k** | 3.609x | 3.61 | 1.1257% | 319,893 |
| **64k** | 3.844x 🏆 | 3.85 | 1.1990% | 300,327 |

### Tokenization Examples

Below are sample sentences tokenized with each vocabulary size:

**Sample 1:** `thumb ⴱⵉ ⴱⵉ ⵙⵉ ⵏⵖ BBC (ⵙ ⵜⵏⴳⵍⵉⵣⵜ: British Broadcasting Corporation) ⵉⵙⴰⵖⵓⵍⵏ`

| Vocab | Tokens | Count |
|-------|--------|-------|
| 8k | `▁thumb ▁ⴱⵉ ▁ⴱⵉ ▁ⵙⵉ ▁ⵏⵖ ▁b bc ▁( ⵙ ▁ⵜⵏⴳⵍⵉⵣⵜ ... (+16 more)` | 26 |
| 16k | `▁thumb ▁ⴱⵉ ▁ⴱⵉ ▁ⵙⵉ ▁ⵏⵖ ▁bbc ▁( ⵙ ▁ⵜⵏⴳⵍⵉⵣⵜ : ... (+9 more)` | 19 |
| 32k | `▁thumb ▁ⴱⵉ ▁ⴱⵉ ▁ⵙⵉ ▁ⵏⵖ ▁bbc ▁( ⵙ ▁ⵜⵏⴳⵍⵉⵣⵜ : ... (+8 more)` | 18 |
| 64k | `▁thumb ▁ⴱⵉ ▁ⴱⵉ ▁ⵙⵉ ▁ⵏⵖ ▁bbc ▁( ⵙ ▁ⵜⵏⴳⵍⵉⵣⵜ : ... (+5 more)` | 15 |

**Sample 2:** `ⴰⴳⴰⴷⴰⵣ ⴰⴼⵕⴰⵏⵚⵉⵚ ⵉⴳⴰ ⴰⴳⴷⵓⵣ ⴷ ⴰⵙⴷⴷⵉ ⵏ ⵡⴰⵙⵖⵏⵣⵉ ⴳ ⵜⴰⴷⴷⵓⵔⵜ ⵜⴰⴼⵕⴰⵏⵚⵉⵚⵜ, ⵏ ⵓⵔⵍⵢⴰⵏⵣ ⴰⵎⴰⵢ...`

| Vocab | Tokens | Count |
|-------|--------|-------|
| 8k | `▁ⴰⴳⴰ ⴷⴰⵣ ▁ⴰⴼⵕⴰⵏⵚⵉⵚ ▁ⵉⴳⴰ ▁ⴰⴳⴷ ⵓⵣ ▁ⴷ ▁ⴰⵙⴷⴷⵉ ▁ⵏ ▁ⵡⴰⵙ ... (+19 more)` | 29 |
| 16k | `▁ⴰⴳⴰⴷⴰⵣ ▁ⴰⴼⵕⴰⵏⵚⵉⵚ ▁ⵉⴳⴰ ▁ⴰⴳⴷ ⵓⵣ ▁ⴷ ▁ⴰⵙⴷⴷⵉ ▁ⵏ ▁ⵡⴰⵙ ⵖⵏⵣⵉ ... (+17 more)` | 27 |
| 32k | `▁ⴰⴳⴰⴷⴰⵣ ▁ⴰⴼⵕⴰⵏⵚⵉⵚ ▁ⵉⴳⴰ ▁ⴰⴳⴷ ⵓⵣ ▁ⴷ ▁ⴰⵙⴷⴷⵉ ▁ⵏ ▁ⵡⴰⵙ ⵖⵏⵣⵉ ... (+17 more)` | 27 |
| 64k | `▁ⴰⴳⴰⴷⴰⵣ ▁ⴰⴼⵕⴰⵏⵚⵉⵚ ▁ⵉⴳⴰ ▁ⴰⴳⴷ ⵓⵣ ▁ⴷ ▁ⴰⵙⴷⴷⵉ ▁ⵏ ▁ⵡⴰⵙ ⵖⵏⵣⵉ ... (+11 more)` | 21 |

**Sample 3:** `ⵄⴱⴷⵍⴼⵜⵜⴰⵃ ⵙⵙⵉⵙⵉ (ⵙ ⵜⴰⵄⵕⴰⴱⵜ: عبد الفتاح السيسي), ⵉⵍⵓⵍ ⴳ 19 ⵏⵓⵡⴰⵏⴱⵉⵔ ⴳ ⵜⵇⴰⵀⵉⵔⵜ, ⵉⴳ...`

| Vocab | Tokens | Count |
|-------|--------|-------|
| 8k | `▁ⵄⴱⴷ ⵍⴼ ⵜⵜⴰ ⵃ ▁ⵙⵙⵉ ⵙⵉ ▁( ⵙ ▁ⵜⴰⵄⵕⴰⴱⵜ : ... (+40 more)` | 50 |
| 16k | `▁ⵄⴱⴷ ⵍⴼ ⵜⵜⴰ ⵃ ▁ⵙⵙⵉ ⵙⵉ ▁( ⵙ ▁ⵜⴰⵄⵕⴰⴱⵜ : ... (+38 more)` | 48 |
| 32k | `▁ⵄⴱⴷⵍⴼ ⵜⵜⴰⵃ ▁ⵙⵙⵉⵙⵉ ▁( ⵙ ▁ⵜⴰⵄⵕⴰⴱⵜ : ▁عبد ▁الف ت ... (+34 more)` | 44 |
| 64k | `▁ⵄⴱⴷⵍⴼ ⵜⵜⴰⵃ ▁ⵙⵙⵉⵙⵉ ▁( ⵙ ▁ⵜⴰⵄⵕⴰⴱⵜ : ▁عبد ▁الفتاح ▁السيسي ... (+27 more)` | 37 |


### Key Findings

- **Best Compression:** 64k achieves 3.844x compression
- **Lowest UNK Rate:** 8k with 0.9549% unknown tokens
- **Trade-off:** Larger vocabularies improve compression but increase model size
- **Recommendation:** 32k vocabulary provides optimal balance for production use

---
## 2. N-gram Model Evaluation

![N-gram Perplexity](visualizations/ngram_perplexity.png)

![N-gram Unique](visualizations/ngram_unique.png)

![N-gram Coverage](visualizations/ngram_coverage.png)

### Results

| N-gram | Variant | Perplexity | Entropy | Unique N-grams | Top-100 Coverage | Top-1000 Coverage |
|--------|---------|------------|---------|----------------|------------------|-------------------|
| **2-gram** | Word | 1,196 | 10.22 | 27,047 | 45.0% | 79.1% |
| **2-gram** | Subword | 278 🏆 | 8.12 | 3,951 | 66.4% | 98.7% |
| **3-gram** | Word | 1,791 | 10.81 | 50,741 | 39.8% | 75.1% |
| **3-gram** | Subword | 1,389 | 10.44 | 30,764 | 34.7% | 83.1% |
| **4-gram** | Word | 3,181 | 11.64 | 96,325 | 36.3% | 68.2% |
| **4-gram** | Subword | 3,814 | 11.90 | 123,122 | 22.6% | 70.8% |
| **5-gram** | Word | 3,890 | 11.93 | 104,452 | 36.6% | 65.2% |
| **5-gram** | Subword | 6,884 | 12.75 | 251,758 | 17.4% | 65.2% |

### Top 5 N-grams by Size

**2-grams (Word):**

| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ⵜⴳⵎⵉⴹⵉ ⵏ` | 30,065 |
| 2 | `ⵏ ⵓⵙⴳⴳⵯⴰⵙ` | 27,531 |
| 3 | `ⵓⵎⴹⴰⵏ ⵏ` | 26,944 |
| 4 | `ⵏ ⵉⵎⵣⴷⴰⵖⵏ` | 24,199 |
| 5 | `ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ` | 24,115 |

**3-grams (Word):**

| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ ⵏ` | 24,115 |
| 2 | `ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ` | 14,960 |
| 3 | `ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ ⵓⵙⵖⵉⵡⵙ` | 14,959 |
| 4 | `ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ` | 14,958 |
| 5 | `ⴳ ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ` | 12,063 |

**4-grams (Word):**

| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ ⵓⵙⵖⵉⵡⵙ` | 14,958 |
| 2 | `ⴳ ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ ⵏ` | 12,063 |
| 3 | `ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏⵏⵙ` | 8,928 |
| 4 | `ⵉⵎⵣⴷⴰⵖⵏ ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ` | 8,927 |
| 5 | `ⴰⵎⴰⵜⴰⵢ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵜⴰⵙⵎⵉⵔⵉⵜ` | 8,927 |

**5-grams (Word):**

| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ` | 8,927 |
| 2 | `ⴰⵎⴰⵜⴰⵢ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ` | 8,927 |
| 3 | `ⵉⵎⵣⴷⴰⵖⵏ ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ ⵓⵙⵖⵉⵡⵙ` | 8,927 |
| 4 | `ⵉⴹⴼⴰⵕ ⵓⵙⵓⵏ ⴰⴷ ⵉ ⵜⵔⴼⵉⵇⵜ` | 8,926 |
| 5 | `ⵍⵎⵖⵔⵉⴱ ⵉⴹⴼⴰⵕ ⵓⵙⵓⵏ ⴰⴷ ⵉ` | 8,926 |

**2-grams (Subword):**

| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `ⵏ _` | 653,035 |
| 2 | `_ ⵏ` | 397,792 |
| 3 | `_ ⵜ` | 364,082 |
| 4 | `_ ⵉ` | 257,899 |
| 5 | `_ ⵓ` | 211,446 |

**3-grams (Subword):**

| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `_ ⵏ _` | 291,650 |
| 2 | `_ ⵜ ⴰ` | 138,650 |
| 3 | `_ ⴳ _` | 115,983 |
| 4 | `ⵏ _ ⵉ` | 106,477 |
| 5 | `ⴰ ⵏ _` | 105,784 |

**4-grams (Subword):**

| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `_ ⵏ _ ⵓ` | 86,083 |
| 2 | `ⵜ _ ⵏ _` | 65,334 |
| 3 | `_ ⵏ _ ⵉ` | 62,419 |
| 4 | `ⵏ _ ⵓ ⵙ` | 60,609 |
| 5 | `_ ⵏ _ ⵜ` | 57,983 |

**5-grams (Subword):**

| Rank | N-gram | Count |
|------|--------|-------|
| 1 | `_ ⵏ _ ⵓ ⵙ` | 51,067 |
| 2 | `ⵎ ⵣ ⴷ ⴰ ⵖ` | 45,993 |
| 3 | `ⴳ ⴳ ⵯ ⴰ ⵙ` | 36,185 |
| 4 | `ⵙ ⴳ ⴳ ⵯ ⴰ` | 36,178 |
| 5 | `_ ⵏ ⵏ ⴰ _` | 35,864 |


### Key Findings

- **Best Perplexity:** 2-gram (subword) with 278
- **Entropy Trend:** Decreases with larger n-grams (more predictable)
- **Coverage:** Top-1000 patterns cover ~65% of corpus
- **Recommendation:** 4-gram or 5-gram for best predictive performance

---
## 3. Markov Chain Evaluation

![Markov Entropy](visualizations/markov_entropy.png)

![Markov Contexts](visualizations/markov_contexts.png)

![Markov Branching](visualizations/markov_branching.png)

### Results

| Context | Variant | Avg Entropy | Perplexity | Branching Factor | Unique Contexts | Predictability |
|---------|---------|-------------|------------|------------------|-----------------|----------------|
| **1** | Word | 0.6673 | 1.588 | 4.36 | 83,258 | 33.3% |
| **1** | Subword | 1.0864 | 2.123 | 8.88 | 1,091 | 0.0% |
| **2** | Word | 0.2718 | 1.207 | 1.69 | 361,700 | 72.8% |
| **2** | Subword | 0.9804 | 1.973 | 6.14 | 9,682 | 2.0% |
| **3** | Word | 0.0879 | 1.063 | 1.19 | 608,815 | 91.2% |
| **3** | Subword | 0.8161 | 1.761 | 3.76 | 59,433 | 18.4% |
| **4** | Word | 0.0448 🏆 | 1.032 | 1.12 | 719,950 | 95.5% |
| **4** | Subword | 0.5524 | 1.466 | 2.41 | 223,378 | 44.8% |

### Generated Text Samples (Word-based)

Below are text samples generated from each word-based Markov chain model:

**Context Size 1:**

1. `ⵏ ⵜⴰⵚⵚⵓⵕⵜ ⵜⴰⵎⵏⴰⴹⵜ ⵏ 800 ⵏ ⵜⴰⵎⴹⵉⵜ ⵙ ⵜⴳⵎⵉⴹⵉ ⵏ ⵍⵎⵏⵣⵍ ⵜⴰⵙⴳⴰ ⵏ ⵓⵙⵍⵎⴷ 95 ⵏ`
2. `ⴳ ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ ⵏ ⵜⵎⵍⵙⴰ ⵢⴰⴹⵏⵉ ⵣⵓⵏ ⴷ 11 ⵏ ⵢⵉⵡⵍ ⴰⵎⵣⵡⴰⵔⵓ 33 85 37 5`
3. `ⴷ ⵉⵔⴰⵔ ⵍⵎⵖⵔⵉⴱ ⵉⴹⴼⴰⵕ ⵓⵙⵓⵏ ⵉⵎⵓⵏⵏ ⵢⵉⵍⵉ ⴳ ⵓⵙⵉⴹⵏ ⴰⵎⴰⴷⴷⵓⴷ ⵏ ⵜⴳⵍⴷⵉⵜ ⵜⴰⵙⴰⵄⵓⴷⵉⵜ ⴳ ⵜⴳⵔⴰⵡⵜ ⵏ`

**Context Size 2:**

1. `ⵜⴳⵎⵉⴹⵉ ⵏ ⵎⴷⴷ ⵏⵏⴰ ⵥⴹⴰⵕⵏⵉⵏ ⵉ ⵜⵡⵓⵔⵉ 53 52 ⴳ ⴰⵢⵜ ⵄⵍⵍⴰ ⵏⵏⴰ ⴳ ⵍⵍⴰⵏ 5 ⵏ`
2. `ⵏ ⵓⵙⴳⴳⵯⴰⵙ démographiques et socio économiques de la population et de l habitat de ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ...`
3. `ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏⵏⵙ 75 ⵏ ⵜⵡⵜⵎⵉⵏ ⵜⴰⵡⵊⵉⵡⵉⵏ ⵉⵡⵍ ⴷ ⵜⴰⵔⵡⴰ ⴳ ⴳⴰⵏ ⵡⵉⵏⴰ ⵢⵉⵡⵍⵏ ⴳ ⵓⵙⵓⵏ`

**Context Size 3:**

1. `ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ ⵏ ⵜⴰⵔⵙⴽⴽⵉⵍⵜ 50 98 ⴳⵔ ⵉⵔⴱⴰⵏ ⴷ ⵜⵔⴱⴰⵜⵉⵏ ⵏⵏⴰ ⵖⵓⵔ ⴳⵔ 6 ⴷ 11 ⵏ ⵓⵙⴳⴳⵯⴰⵙ`
2. `ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏⵏⵙ 122 ⵏ ⵓⵎⵣⴷⴰⵖ ⴳ ⵓⵙⵉⴹⵏ ⴰⵎⴰⴷⴷⵓⴷ ⵏ ⵓⵙⴳⴳⵯⴰⵙ démographiques et socio économiques de la`
3. `ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ ⵓⵙⵖⵉⵡⵙ ⴰⵕⵛⵉⴼ 14 ⵖⵓⵛⵜ ⵜⵉⵙⵏⴰⴷⴷⴰⴷⵉⵏ ⵜⵉⵙⵏⴰⴷⴷⴰⴷⵉⵏ ⵜⵉⵎⴰⵜⴰⵢⵉⵏ ⵉⴳⴳⵯⵉⵣ ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏ ⵜⴰⵖⵣⵓⵜ ⵙ...`

**Context Size 4:**

1. `ⵜⴰⵙⵎⵉⵔⵉⵜ ⵜⴰⵎⴰⵜⵜⴰⵢⵜ ⵏ ⵓⵙⵖⵉⵡⵙ ⴰⵕⵛⵉⴼ 14 ⵖⵓⵛⵜ ⵜⵉⵙⵏⴰⴷⴷⴰⴷⵉⵏ ⵜⵉⵙⵏⴰⴷⴷⴰⴷⵉⵏ ⵜⵉⵎⴰⵜⴰⵢⵉⵏ ⵉⴳⴳⵯⵉⵣ ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏ...`
2. `ⴳ ⵜⵍⴽⵎ ⵜⴳⵎⵉⴹⵉ ⵏ ⵎⴷⴷ ⵏⵏⴰ ⵥⴹⴰⵕⵏⵉⵏ ⵉ ⵜⵡⵓⵔⵉ 55 29 ⴳ ⴰⵢⵜ ⴱⵏ ⵄⴱⴱⵓ ⴰⵔ ⵏⵉⵜ ⵙⵡⵓⵔⵉⵏ ⵏⵉⵖ`
3. `ⵓⵎⴹⴰⵏ ⵏ ⵉⵎⵣⴷⴰⵖⵏ ⵏⵏⵙ 390 ⵏ ⵓⵎⵣⴷⴰⵖ ⴳ ⵓⵙⵉⴹⵏ ⴰⵎⴰⴷⴷⵓⴷ ⵏ ⵓⵙⴳⴳⵯⴰⵙ démographiques et socio économiques de la...`


### Generated Text Samples (Subword-based)

Below are text samples generated from each subword-based Markov chain model:

**Context Size 1:**

1. `_ⵜⴰⵢⵢⵉⵏⴰⵔ_ⴱⵜⴰⵏ_ⵓ`
2. `ⴰⵖⵉⵜ_ⵖⵜ_ⵇⵏ_ⴳ_non`
3. `ⵏ_ⵉⵇⵜⴰ_ⵏ_ⵓⵎⴹⵏ_ⴼⵜ`

**Context Size 2:**

1. `ⵏ_ⴷ_ⵉⴳⴳⵉⵙⵙ_3_ⴰⵍ_ⴰ`
2. `_ⵏ_ⴰⵎⴰⵏ_ⴳ_ⵓⵙⵙⴰⵖⵏ_`
3. `_ⵜⵡⵓⵔ_6_ⴽⵓⴷⴰⵖ,_ⵉⵥ`

**Context Size 3:**

1. `_ⵏ_ⵜⴰⵙⵡⵉⵏ_ⵉⵙⴽⴰⵔⵏⵜ_`
2. `_ⵜⴰⵡⵓⵔⵉ_4.52%_ⴳⵔ_6`
3. `_ⴳ_ⵍⵍⴰⵏ_ⵡⵉⵏ:_ⵉⵡⵜⵎⵉ`

**Context Size 4:**

1. `_ⵏ_ⵓⵍⴰ_ⴳ_ⴳⴰⵏ_ⵡⵉⵏⴰ_ⵢ`
2. `ⵜ_ⵏ_ⵓⵙⵖⵉⵡⵙ._ⴰⵕⵛⵉⴼ,_`
3. `_ⵏ_ⵉⵡⵜⵎⴰⵏ_ⴷ_24.85,_`


### Key Findings

- **Best Predictability:** Context-4 (word) with 95.5% predictability
- **Branching Factor:** Decreases with context size (more deterministic)
- **Memory Trade-off:** Larger contexts require more storage (223,378 contexts)
- **Recommendation:** Context-3 or Context-4 for text generation

---
## 4. Vocabulary Analysis

![Zipf's Law](visualizations/zipf_law.png)

![Top Words](visualizations/top20_words.png)

![Coverage Curve](visualizations/vocab_coverage.png)

### Statistics

| Metric | Value |
|--------|-------|
| Vocabulary Size | 35,191 |
| Total Tokens | 2,431,531 |
| Mean Frequency | 69.10 |
| Median Frequency | 4 |
| Frequency Std Dev | 1880.39 |

### Most Common Words

| Rank | Word | Frequency |
|------|------|-----------|
| 1 | ⵏ | 291,759 |
| 2 | ⴳ | 116,564 |
| 3 | ⴷ | 74,542 |
| 4 | ⵙ | 39,445 |
| 5 | ⵏⵏⴰ | 35,886 |
| 6 | ⴳⵔ | 30,891 |
| 7 | ⵉⵎⵣⴷⴰⵖⵏ | 30,462 |
| 8 | ⵜⴳⵎⵉⴹⵉ | 30,068 |
| 9 | ⵓⵙⴳⴳⵯⴰⵙ | 29,018 |
| 10 | ⵓⵎⴹⴰⵏ | 27,041 |

### Least Common Words (from vocabulary)

| Rank | Word | Frequency |
|------|------|-----------|
| 1 | ⵓⵎⵙⵙⵉⵥⵉⵕ | 2 |
| 2 | ⵜⵙⵔⴽⵎⵉⵏ | 2 |
| 3 | ⵓⵎⵢⴰⴱⴰ | 2 |
| 4 | fourth | 2 |
| 5 | ⵜⴰⴱⵔⵓⵙⵉⵜ | 2 |
| 6 | ⵜⴰⵙⵏⴽⵜⴰ | 2 |
| 7 | ⵜⵉⵣⵎⵣⴰⵏⵉⵏ | 2 |
| 8 | ⵜⴰⴷⵓⵥⴽⵉⵡⵜ | 2 |
| 9 | ⴰⵎⵥⵕⴷⴳⴰⵔ | 2 |
| 10 | ⵜⴰⵥⵕⵎⴰⵔⴽⵙⵉⵜ | 2 |

### Zipf's Law Analysis

| Metric | Value |
|--------|-------|
| Zipf Coefficient | 1.2553 |
| R² (Goodness of Fit) | 0.991414 |
| Adherence Quality | **excellent** |

### Coverage Analysis

| Top N Words | Coverage |
|-------------|----------|
| Top 100 | 67.5% |
| Top 1,000 | 88.5% |
| Top 5,000 | 94.6% |
| Top 10,000 | 96.7% |

### Key Findings

- **Zipf Compliance:** R²=0.9914 indicates excellent adherence to Zipf's law
- **High Frequency Dominance:** Top 100 words cover 67.5% of corpus
- **Long Tail:** 25,191 words needed for remaining 3.3% coverage

---
## 5. Word Embeddings Evaluation

![Embedding Isotropy](visualizations/embedding_isotropy.png)

![Similarity Matrix](visualizations/embedding_similarity.png)

![t-SNE Words](visualizations/tsne_words.png)

![t-SNE Sentences](visualizations/tsne_sentences.png)


### 5.1 Cross-Lingual Alignment

![Alignment Quality](visualizations/embedding_alignment_quality.png)

![Multilingual t-SNE](visualizations/embedding_tsne_multilingual.png)


### 5.2 Model Comparison

| Model | Dimension | Isotropy | Semantic Density | Alignment R@1 | Alignment R@10 |
|-------|-----------|----------|------------------|---------------|----------------|
| **mono_32d** | 32 | 0.7259 🏆 | 0.3600 | N/A | N/A |
| **mono_64d** | 64 | 0.5835 | 0.3114 | N/A | N/A |
| **mono_128d** | 128 | 0.1766 | 0.3125 | N/A | N/A |
| **aligned_32d** | 32 | 0.7259 | 0.3745 | 0.0080 | 0.0540 |
| **aligned_64d** | 64 | 0.5835 | 0.3265 | 0.0120 | 0.1240 |
| **aligned_128d** | 128 | 0.1766 | 0.3192 | 0.0360 | 0.1480 |

### Key Findings

- **Best Isotropy:** mono_32d with 0.7259 (more uniform distribution)
- **Semantic Density:** Average pairwise similarity of 0.3340. Lower values indicate better semantic separation.
- **Alignment Quality:** Aligned models achieve up to 3.6% R@1 in cross-lingual retrieval.
- **Recommendation:** 128d aligned for best cross-lingual performance

---
## 6.  Morphological Analysis (Experimental)

This section presents an automated morphological analysis derived from the statistical divergence between word-level and subword-level models. By analyzing where subword predictability spikes and where word-level coverage fails, we can infer linguistic structures without supervised data.

### 6.1 Productivity & Complexity

| Metric | Value | Interpretation | Recommendation |
|--------|-------|----------------|----------------|
| Productivity Index | **5.000** | High morphological productivity | Reliable analysis |
| Idiomaticity Gap | **0.001** | Low formulaic content | - |

### 6.2 Affix Inventory (Productive Units)

These are the most productive prefixes and suffixes identified by sampling the vocabulary for global substitutability patterns. A unit is considered an affix if stripping it leaves a valid stem that appears in other contexts.

#### Productive Prefixes
| Prefix | Examples |
|--------|----------|
| `-ⵜ` | ⵜⵉⵎⵙⵙⵉ, ⵜⴳⵎⴰⵎⵜ, ⵜⵛⴰⵡⵉⵜ |
| `-ⵜⴰ` | ⵜⴰⵎⴰⴽⵓⴷⵜ, ⵜⴰⴱⵕⵕⴰⵏⵉⵢⵜ, ⵜⴰⵇⵇⴰⵢⵜ |
| `-ⵉ` | ⵉⵙⵙⵏⵄⴰⵜ, ⵉⴳⵯⵔⵔⴰⵎⵏ, ⵉⵊ |
| `-ⴰ` | ⴰⵎⵙⵏⴽⴰⵔ, ⴰⵜⵉⵍⵉⴼⵉⵣⵢⵓⵏ, ⴰⵎⵖⵔⵉⴱⵉⵢ |
| `-ⵓ` | ⵓⵊⵔⵉ, ⵓⴳⵜⴷⵉⵙ, ⵓⵔⵔⴰⵡ |
| `-ⵜⵉ` | ⵜⵉⵎⵙⵙⵉ, ⵜⵉⵎⵥⴰⵕⵕⵓⵕⵉⵏ, ⵜⵉⵎⵥⵍⴰⵢⵉⵏ |
| `-ⵍ` | ⵍⵃⵓⵎⴰ, ⵍⵡⴰⴷ, ⵍⴳⵯⵍⵍⴰ |
| `-ⵉⵎ` | ⵉⵎⵥⵉⵏⵛⵓⵜⴰⵏⴱⵉⵔ, ⵉⵎⵢⴰⴳⴰⵔ, ⵉⵎⴷⴰⵏ |

#### Productive Suffixes
| Suffix | Examples |
|--------|----------|
| `-ⵏ` | ⴽⵔⵓⵛⵏ, ⵉⴳⵯⵔⵔⴰⵎⵏ, ⵜⵉⵎⵥⴰⵕⵕⵓⵕⵉⵏ |
| `-ⵜ` | ⵜⴳⵎⴰⵎⵜ, ⵜⵛⴰⵡⵉⵜ, ⵉⵙⵙⵏⵄⴰⵜ |
| `-ⵉⵏ` | ⵜⵉⵎⵥⴰⵕⵕⵓⵕⵉⵏ, ⵣⵣⵏⵣⴰⵏⵉⵏ, ⵜⵉⵎⵥⵍⴰⵢⵉⵏ |
| `-ⴰ` | ⴱⵓⴷⴰ, ⵊⴰⵎⴰⵢⴽⴰ, ⵍⵃⵓⵎⴰ |
| `-ⵉ` | ⵜⵉⵎⵙⵙⵉ, ⵓⵊⵔⵉ, ⵏⵜⵜⵉⵏⵉ |
| `-ⴰⵏ` | ⵉⴱⵇⵇⴰⵏ, ⵎⵛⴰⵛⴽⴰⵏ, ⵉⵎⴷⴰⵏ |
| `-ⵉⵜ` | ⵜⵛⴰⵡⵉⵜ, ⵜⴰⴷⵉⵏⴰⵎⵉⵜ, ⴱⵓⵜⵓⵏⴼⵉⵜ |
| `-ⵔ` | ⴰⵎⵙⵏⴽⴰⵔ, ⵜⵜⵔ, ⵉⵎⵥⵉⵏⵛⵓⵜⴰⵏⴱⵉⵔ |

### 6.3 Bound Stems (Lexical Roots)

Bound stems are high-frequency subword units that are semantically cohesive but rarely appear as standalone words. These often correspond to the 'core' of a word that requires inflection or derivation to be valid.

| Stem | Cohesion | Substitutability | Examples |
|------|----------|------------------|----------|
| `ⴰⴷⴷⴰ` | 1.60x | 54 contexts | ⵜⴰⴷⴷⴰ, ⴰⴷⴷⴰⴳ, ⵢⴰⴷⴷⴰ |
| `ⵡⵓⵔⵉ` | 1.73x | 38 contexts | ⵜⵡⵓⵔⵉ, ⵜⵙⵡⵓⵔⵉ, ⴰⵙⵡⵓⵔⵉ |
| `ⴳⴳⴰⵔ` | 1.70x | 24 contexts | ⵉⴳⴳⴰⵔ, ⴳⴳⴰⵔⵏ, ⵓⴳⴳⴰⵔ |
| `ⵓⴳⴳⴰ` | 1.65x | 24 contexts | ⵢⵓⴳⴳⴰ, ⵜⵓⴳⴳⴰ, ⵓⴳⴳⴰⵏ |
| `ⵜⵜⴰⵢ` | 1.71x | 19 contexts | ⴰⵜⵜⴰⵢ, ⵓⵡⵜⵜⴰⵢ, ⵓⵏⵜⵜⴰⵢ |
| `ⴰⵜⵜⴰ` | 1.62x | 22 contexts | ⴰⵜⵜⴰⵢ, ⵎⴰⵜⵜⴰ, ⴰⵜⵜⴰⵖ |
| `ⵎⵉⵔⵉ` | 1.54x | 21 contexts | ⵉⵎⵉⵔⵉ, ⵓⵎⵉⵔⵉⴳ, ⵜⵎⵉⵔⵉⵜ |
| `ⴷⴷⴰⴷ` | 1.66x | 16 contexts | ⵃⴷⴷⴰⴷ, ⵓⴷⴷⴰⴷ, ⵉⴷⴷⴰⴷ |
| `ⴰⵎⴰⵜ` | 1.50x | 17 contexts | ⴰⵎⴰⵜⵓ, ⴰⵎⴰⵜⴰ, ⴰⵎⴰⵜⵜⵓ |
| `ⵙⵍⵎⴷ` | 1.69x | 12 contexts | ⴰⵙⵍⵎⴷ, ⵓⵙⵍⵎⴷ, ⵙⵍⵎⴷⵏ |
| `ⵉⵔⵉⵜ` | 1.59x | 14 contexts | ⵜⵉⵔⵉⵜ, ⵙⵉⵔⵉⵜ, ⵙⴱⵉⵔⵉⵜ |
| `ⴰⵢⵉⵏ` | 1.86x | 9 contexts | ⴼⵍⴰⵢⵉⵏ, ⵜⵎⴷⴰⵢⵉⵏ, ⵜⵓⵎⴰⵢⵉⵏ |

### 6.4 Affix Compatibility (Co-occurrence)

This table shows which prefixes and suffixes most frequently co-occur on the same stems, revealing the 'stacking' rules of the language's morphology.

| Prefix | Suffix | Frequency | Examples |
|--------|--------|-----------|----------|
| `-ⵜ` | `-ⵜ` | 684 words | ⵜⴰⴱⵔⵓⵜⵉⵙⵜⴰⵏⵜⵉⵜ, ⵜⴰⵏⵓⵍⴼⵓⵜ |
| `-ⵉ` | `-ⵏ` | 523 words | ⵉⴼⵓⵄⵣⵏ, ⵉⵎⵙⴷⵎⴰⵔⵏ |
| `-ⵜ` | `-ⵏ` | 379 words | ⵜⵢⴰⴼⵓⵜⵉⵏ, ⵜⵉⵕⵚⵍⵉⵢⵉⵏ |
| `-ⵜ` | `-ⵉⵏ` | 331 words | ⵜⵢⴰⴼⵓⵜⵉⵏ, ⵜⵉⵕⵚⵍⵉⵢⵉⵏ |
| `-ⵜ` | `-ⵉⵜ` | 130 words | ⵜⴰⴱⵔⵓⵜⵉⵙⵜⴰⵏⵜⵉⵜ, ⵜⴰⵊⵓⴳⵕⴰⴼⵉⵜ |
| `-ⵍ` | `-ⴰ` | 101 words | ⵍⴼⴰⵢⴹⴰ, ⵍⴱⵕⵕⴰⵏⵢⵢⴰ |
| `-ⵜ` | `-ⴰ` | 74 words | ⵜⵜⵓⴱⵏⴰ, ⵜⴰⵎⴰ |
| `-ⵉ` | `-ⴰⵏ` | 63 words | ⵉⵎⵛⴰⵛⴽⴰⵏ, ⵉⵡⴷⴰⵏ |
| `-ⴰ` | `-ⵏ` | 58 words | ⴰⵀⵉⵍⵏ, ⴰⵎⴽⴰⵏ |
| `-ⴰ` | `-ⵉ` | 47 words | ⴰⵎⵣⴳⵉ, ⴰⴷⵡⴰⵍⵉ |

### 6.5 Recursive Morpheme Segmentation

Using **Recursive Hierarchical Substitutability**, we decompose complex words into their constituent morphemes. This approach handles nested affixes (e.g., `prefix-prefix-root-suffix`).

| Word | Suggested Split | Confidence | Stem |
|------|-----------------|------------|------|
| ⵜⵉⵔⵍⵓⴳⵏⴰⵏⵉⵏ | **`ⵜⵉⵔⵍⵓⴳⵏⴰ-ⵏ-ⵉⵏ`** | 7.5 | `ⵏ` |
| ⵜⴳⵔⴰⵖⵍⴰⵏⵉⵏ | **`ⵜⴳⵔⴰⵖⵍⴰ-ⵏ-ⵉⵏ`** | 7.5 | `ⵏ` |
| ⵜⵜⵄⵕⵕⴱⵏⵉⵏ | **`ⵜⵜⵄⵕⵕⴱ-ⵏ-ⵉⵏ`** | 7.5 | `ⵏ` |
| ⵉⵜⵜⴰⵡⵙⵙⴰⵏⵏ | **`ⵉⵜⵜⴰⵡⵙⵙⴰ-ⵏ-ⵏ`** | 7.5 | `ⵏ` |
| ⵉⵎⵖⵔⴰⴷⴰⵏⵏ | **`ⵉⵎⵖⵔⴰⴷⴰ-ⵏ-ⵏ`** | 7.5 | `ⵏ` |
| ⵜⵉⵎⴰⵙⵉⵏⵉⵏ | **`ⵜⵉⵎⴰⵙ-ⵉⵏ-ⵉⵏ`** | 7.5 | `ⵉⵏ` |
| ⵉⵙⵉⵏⴰⵔⵢⵓⵜⵏ | **`ⵉⵙⵉⵏⴰⵔⵢⵓ-ⵜ-ⵏ`** | 7.5 | `ⵜ` |
| ⵜⵉⵙⵏⵛⵏⵢⴰⵍⴰⵏⵉⵏ | **`ⵜⵉⵙⵏⵛⵏⵢⴰⵍ-ⴰⵏ-ⵉⵏ`** | 7.5 | `ⴰⵏ` |
| ⴽⵔⵉⵙⵜⵢⴰⵏⵓ | **`ⴽⵔⵉⵙⵜⵢⴰ-ⵏ-ⵓ`** | 7.5 | `ⵏ` |
| ⵜⵜⵓⵙⵎⵔⴰⵙⵏⵉⵏ | **`ⵜⵜⵓⵙⵎⵔⴰⵙ-ⵏ-ⵉⵏ`** | 7.5 | `ⵏ` |
| ⵜⵉⵎⵢⴰⵇⴰⵏⵉⵏ | **`ⵜⵉⵎⵢⴰⵇ-ⴰⵏ-ⵉⵏ`** | 7.5 | `ⴰⵏ` |
| ⵜⵉⵏⵎⴹⴰⵏⵉⵏ | **`ⵜⵉⵏⵎⴹ-ⴰⵏ-ⵉⵏ`** | 7.5 | `ⴰⵏ` |
| ⵜⵜⵡⴰⵙⵙⴰⵏⵏⵜ | **`ⵜⵜⵡⴰⵙⵙⴰⵏ-ⵏ-ⵜ`** | 7.5 | `ⵏ` |
| ⵉⵙⵜⵓⴷⵢⵓⵜⵏ | **`ⵉⵙⵜⵓⴷⵢⵓ-ⵜ-ⵏ`** | 7.5 | `ⵜ` |
| ⵉⵜⵜⵓⵙⵖⵥⵏⵏ | **`ⵉⵜⵜⵓⵙⵖⵥ-ⵏ-ⵏ`** | 7.5 | `ⵏ` |

### 6.6 Linguistic Interpretation

> **Automated Insight:**
The language Standard Moroccan Tamazight shows high morphological productivity. The subword models are significantly more efficient than word models, suggesting a rich system of affixation or compounding.

---
## 7. Summary & Recommendations

![Performance Dashboard](visualizations/performance_dashboard.png)

### Production Recommendations

| Component | Recommended | Rationale |
|-----------|-------------|-----------|
| Tokenizer | **64k BPE** | Best compression (3.84x) |
| N-gram | **2-gram** | Lowest perplexity (278) |
| Markov | **Context-4** | Highest predictability (95.5%) |
| Embeddings | **100d** | Balanced semantic capture and isotropy |


---
## Appendix: Metrics Glossary & Interpretation Guide

This section provides definitions, intuitions, and guidance for interpreting the metrics used throughout this report.

### Tokenizer Metrics

**Compression Ratio**
> *Definition:* The ratio of characters to tokens (chars/token). Measures how efficiently the tokenizer represents text.
>
> *Intuition:* Higher compression means fewer tokens needed to represent the same text, reducing sequence lengths for downstream models. A 3x compression means ~3 characters per token on average.
>
> *What to seek:* Higher is generally better for efficiency, but extremely high compression may indicate overly aggressive merging that loses morphological information.

**Average Token Length (Fertility)**
> *Definition:* Mean number of characters per token produced by the tokenizer.
>
> *Intuition:* Reflects the granularity of tokenization. Longer tokens capture more context but may struggle with rare words; shorter tokens are more flexible but increase sequence length.
>
> *What to seek:* Balance between 2-5 characters for most languages. Arabic/morphologically-rich languages may benefit from slightly longer tokens.

**Unknown Token Rate (OOV Rate)**
> *Definition:* Percentage of tokens that map to the unknown/UNK token, indicating words the tokenizer cannot represent.
>
> *Intuition:* Lower OOV means better vocabulary coverage. High OOV indicates the tokenizer encounters many unseen character sequences.
>
> *What to seek:* Below 1% is excellent; below 5% is acceptable. BPE tokenizers typically achieve very low OOV due to subword fallback.

### N-gram Model Metrics

**Perplexity**
> *Definition:* Measures how "surprised" the model is by test data. Mathematically: 2^(cross-entropy). Lower values indicate better prediction.
>
> *Intuition:* If perplexity is 100, the model is as uncertain as if choosing uniformly among 100 options at each step. A perplexity of 10 means effectively choosing among 10 equally likely options.
>
> *What to seek:* Lower is better. Perplexity decreases with larger n-grams (more context). Values vary widely by language and corpus size.

**Entropy**
> *Definition:* Average information content (in bits) needed to encode the next token given the context. Related to perplexity: perplexity = 2^entropy.
>
> *Intuition:* High entropy means high uncertainty/randomness; low entropy means predictable patterns. Natural language typically has entropy between 1-4 bits per character.
>
> *What to seek:* Lower entropy indicates more predictable text patterns. Entropy should decrease as n-gram size increases.

**Coverage (Top-K)**
> *Definition:* Percentage of corpus occurrences explained by the top K most frequent n-grams.
>
> *Intuition:* High coverage with few patterns indicates repetitive/formulaic text; low coverage suggests diverse vocabulary usage.
>
> *What to seek:* Depends on use case. For language modeling, moderate coverage (40-60% with top-1000) is typical for natural text.

### Markov Chain Metrics

**Average Entropy**
> *Definition:* Mean entropy across all contexts, measuring average uncertainty in next-word prediction.
>
> *Intuition:* Lower entropy means the model is more confident about what comes next. Context-1 has high entropy (many possible next words); Context-4 has low entropy (few likely continuations).
>
> *What to seek:* Decreasing entropy with larger context sizes. Very low entropy (<0.1) indicates highly deterministic transitions.

**Branching Factor**
> *Definition:* Average number of unique next tokens observed for each context.
>
> *Intuition:* High branching = many possible continuations (flexible but uncertain); low branching = few options (predictable but potentially repetitive).
>
> *What to seek:* Branching factor should decrease with context size. Values near 1.0 indicate nearly deterministic chains.

**Predictability**
> *Definition:* Derived metric: (1 - normalized_entropy) × 100%. Indicates how deterministic the model's predictions are.
>
> *Intuition:* 100% predictability means the next word is always certain; 0% means completely random. Real text falls between these extremes.
>
> *What to seek:* Higher predictability for text generation quality, but too high (>98%) may produce repetitive output.

### Vocabulary & Zipf's Law Metrics

**Zipf's Coefficient**
> *Definition:* The slope of the log-log plot of word frequency vs. rank. Zipf's law predicts this should be approximately -1.
>
> *Intuition:* A coefficient near -1 indicates the corpus follows natural language patterns where a few words are very common and most words are rare.
>
> *What to seek:* Values between -0.8 and -1.2 indicate healthy natural language distribution. Deviations may suggest domain-specific or artificial text.

**R² (Coefficient of Determination)**
> *Definition:* Measures how well the linear fit explains the frequency-rank relationship. Ranges from 0 to 1.
>
> *Intuition:* R² near 1.0 means the data closely follows Zipf's law; lower values indicate deviation from expected word frequency patterns.
>
> *What to seek:* R² > 0.95 is excellent; > 0.99 indicates near-perfect Zipf adherence typical of large natural corpora.

**Vocabulary Coverage**
> *Definition:* Cumulative percentage of corpus tokens accounted for by the top N words.
>
> *Intuition:* Shows how concentrated word usage is. If top-100 words cover 50% of text, the corpus relies heavily on common words.
>
> *What to seek:* Top-100 covering 30-50% is typical. Higher coverage indicates more repetitive text; lower suggests richer vocabulary.

### Word Embedding Metrics

**Isotropy**
> *Definition:* Measures how uniformly distributed vectors are in the embedding space. Computed as the ratio of minimum to maximum singular values.
>
> *Intuition:* High isotropy (near 1.0) means vectors spread evenly in all directions; low isotropy means vectors cluster in certain directions, reducing expressiveness.
>
> *What to seek:* Higher isotropy generally indicates better-quality embeddings. Values > 0.1 are reasonable; > 0.3 is good. Lower-dimensional embeddings tend to have higher isotropy.

**Average Norm**
> *Definition:* Mean magnitude (L2 norm) of word vectors in the embedding space.
>
> *Intuition:* Indicates the typical "length" of vectors. Consistent norms suggest stable training; high variance may indicate some words are undertrained.
>
> *What to seek:* Relatively consistent norms across models. The absolute value matters less than consistency (low std deviation).

**Cosine Similarity**
> *Definition:* Measures angular similarity between vectors, ranging from -1 (opposite) to 1 (identical direction).
>
> *Intuition:* Words with similar meanings should have high cosine similarity. This is the standard metric for semantic relatedness in embeddings.
>
> *What to seek:* Semantically related words should score > 0.5; unrelated words should be near 0. Synonyms often score > 0.7.

**t-SNE Visualization**
> *Definition:* t-Distributed Stochastic Neighbor Embedding - a dimensionality reduction technique that preserves local structure for visualization.
>
> *Intuition:* Clusters in t-SNE plots indicate groups of semantically related words. Spread indicates vocabulary diversity; tight clusters suggest semantic coherence.
>
> *What to seek:* Meaningful clusters (e.g., numbers together, verbs together). Avoid over-interpreting distances - t-SNE preserves local, not global, structure.

### General Interpretation Guidelines

1. **Compare within model families:** Metrics are most meaningful when comparing models of the same type (e.g., 8k vs 64k tokenizer).
2. **Consider trade-offs:** Better performance on one metric often comes at the cost of another (e.g., compression vs. OOV rate).
3. **Context matters:** Optimal values depend on downstream tasks. Text generation may prioritize different metrics than classification.
4. **Corpus influence:** All metrics are influenced by corpus characteristics. Wikipedia text differs from social media or literature.
5. **Language-specific patterns:** Morphologically rich languages (like Arabic) may show different optimal ranges than analytic languages.


### Visualizations Index

| Visualization | Description |
|---------------|-------------|
| Tokenizer Compression | Compression ratios by vocabulary size |
| Tokenizer Fertility | Average token length by vocabulary |
| Tokenizer OOV | Unknown token rates |
| Tokenizer Total Tokens | Total tokens by vocabulary |
| N-gram Perplexity | Perplexity by n-gram size |
| N-gram Entropy | Entropy by n-gram size |
| N-gram Coverage | Top pattern coverage |
| N-gram Unique | Unique n-gram counts |
| Markov Entropy | Entropy by context size |
| Markov Branching | Branching factor by context |
| Markov Contexts | Unique context counts |
| Zipf's Law | Frequency-rank distribution with fit |
| Vocab Frequency | Word frequency distribution |
| Top 20 Words | Most frequent words |
| Vocab Coverage | Cumulative coverage curve |
| Embedding Isotropy | Vector space uniformity |
| Embedding Norms | Vector magnitude distribution |
| Embedding Similarity | Word similarity heatmap |
| Nearest Neighbors | Similar words for key terms |
| t-SNE Words | 2D word embedding visualization |
| t-SNE Sentences | 2D sentence embedding visualization |
| Position Encoding | Encoding method comparison |
| Model Sizes | Storage requirements |
| Performance Dashboard | Comprehensive performance overview |

---
## About This Project

### Data Source

Models trained on [wikipedia-monthly](https://huggingface.co/datasets/omarkamali/wikipedia-monthly) - a monthly snapshot of Wikipedia articles across 300+ languages.

### Project

A project by **[Wikilangs](https://wikilangs.org)** - Open-source NLP models for every Wikipedia language.

### Maintainer

[Omar Kamali](https://omarkamali.com) - [Omneity Labs](https://omneitylabs.com)

### Citation

If you use these models in your research, please cite:

```bibtex
@misc{wikilangs2025,
  author = {Kamali, Omar},
  title = {Wikilangs: Open NLP Models for Wikipedia Languages},
  year = {2025},
  doi = {10.5281/zenodo.18073153},
  publisher = {Zenodo},
  url = {https://huggingface.co/wikilangs}
  institution = {Omneity Labs}
}
```

### License

MIT License - Free for academic and commercial use.

### Links

- 🌐 Website: [wikilangs.org](https://wikilangs.org)
- 🤗 Models: [huggingface.co/wikilangs](https://huggingface.co/wikilangs)
- 📊 Data: [wikipedia-monthly](https://huggingface.co/datasets/omarkamali/wikipedia-monthly)
- 👤 Author: [Omar Kamali](https://huggingface.co/omarkamali)
- 🤝 Sponsor: [Featherless AI](https://featherless.ai)
---
*Generated by Wikilangs Models Pipeline*

*Report Date: 2026-01-11 05:56:32*