Menu
Reports of my experiments:
- Lexicon Analysis (Jun 15, 2022)
- Content Analysis (Oct 17, 2022)
- Comparative Analysis (Oct 21, 2022)
- Token Analysis (May 9, 2023)
- Token Error Analysis (September 29, 2023)
- Multilingual Model Experiment (April 12, 2024)
Details on some of the results:
- Bar charts (Token analysis)
- Comparison of transcriptions errors (Token Error analysis)
- Diagrams (POS) (Content analysis)
- Distribution of the alphabet by characters (Multilingual model)
- Distribution of the alphabet by language (Multilingual model)
- General distribution of the alphabet (Multilingual model)
- Heatmaps of common ngrams (Multilingual model)
- Metrics (Comparative analysis)
- Metrics (Multilingual model)
- Model testing (Lexicon analysis)
- Popular tokens (Token analysis)
- Table of token error analysis by bigrams (Token error analysis)
- Table EHRI of token error analysis by bigrams (Multilingual model)
- Table of token error analysis by trigrams (Token error analysis)
- Table EHRI of token error analysis by trigrams (Multilingual model)
- Table of token error analysis by tetragrams (Token error analysis)
- Table EHRI of token error analysis by tetragrams (Multilingual model)
- Table of results (Content analysis)
- Table of results (Token analysis)
- Table of results (Token error analysis)
- Table of results (Multilingual model)
- Versus text (Comparative analysis)
- Versus text (Multilingual model)
- Wordclouds (Content analysis)
- Wordclouds (Lexicon analysis)
Additionals informations: