home.social

#htr — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #htr, aggregated by home.social.

fetched live
  1. From text recognition to text analysis: At the digital FGHO Summerschool (24–28 Aug) you'll transcribe sources with #Transkribus & analyze them with #CATMA.

    Working on a project with historical sources? Sign up by Aug 16 for this workshop (held in German)! 👇
    fgho.eu/de/summerschool/2026-q

    #DigitalHumanities #DigitalHistory #DH #HTR #Annotation

  2. From text recognition to text analysis: At the digital FGHO Summerschool (24–28 Aug) you'll transcribe sources with #Transkribus & analyze them with #CATMA.

    Working on a project with historical sources? Sign up by Aug 16 for this workshop (held in German)! 👇
    fgho.eu/de/summerschool/2026-q

    #DigitalHumanities #DigitalHistory #DH #HTR #Annotation

  3. From text recognition to text analysis: At the digital FGHO Summerschool (24–28 Aug) you'll transcribe sources with #Transkribus & analyze them with #CATMA.

    Working on a project with historical sources? Sign up by Aug 16 for this workshop (held in German)! 👇
    fgho.eu/de/summerschool/2026-q

    #DigitalHumanities #DigitalHistory #DH #HTR #Annotation

  4. From text recognition to text analysis: At the digital FGHO Summerschool (24–28 Aug) you'll transcribe sources with #Transkribus & analyze them with #CATMA.

    Working on a project with historical sources? Sign up by Aug 16 for this workshop (held in German)! 👇
    fgho.eu/de/summerschool/2026-q

    #DigitalHumanities #DigitalHistory #DH #HTR #Annotation

  5. From text recognition to text analysis: At the digital FGHO Summerschool (24–28 Aug) you'll transcribe sources with #Transkribus & analyze them with #CATMA.

    Working on a project with historical sources? Sign up by Aug 16 for this workshop (held in German)! 👇
    fgho.eu/de/summerschool/2026-q

    #DigitalHumanities #DigitalHistory #DH #HTR #Annotation

  6. Bookmarked: HTRMoPo App htrmopo.inria.fr/ #HTR Kraken model catalog, built on the HTRMoPo scheme.

  7. Bookmarked: HTRMoPo App htrmopo.inria.fr/ #HTR Kraken model catalog, built on the HTRMoPo scheme.

  8. Bookmarked: HTRMoPo App htrmopo.inria.fr/ #HTR Kraken model catalog, built on the HTRMoPo scheme.

  9. Bookmarked: HTRMoPo App htrmopo.inria.fr/ #HTR Kraken model catalog, built on the HTRMoPo scheme.

  10. [Veille] MOOC « Automatiser la reconnaissance de texte pour les SHS » : introduction à la reconnaissance automatique d’écriture appliquée aux documents historiques by @biblissima.bsky.social ; #CIHAMUMR5648 inside ! 25images.msh-lse.fr/portails/m
    #ATR #HTR #deeplearning #mooc #digitalhumanities

  11. [Veille] MOOC « Automatiser la reconnaissance de texte pour les SHS » : introduction à la reconnaissance automatique d’écriture appliquée aux documents historiques by @biblissima.bsky.social ; #CIHAMUMR5648 inside ! 25images.msh-lse.fr/portails/m
    #ATR #HTR #deeplearning #mooc #digitalhumanities

  12. [Veille] MOOC « Automatiser la reconnaissance de texte pour les SHS » : introduction à la reconnaissance automatique d’écriture appliquée aux documents historiques by @biblissima.bsky.social ; #CIHAMUMR5648 inside ! 25images.msh-lse.fr/portails/m
    #ATR #HTR #deeplearning #mooc #digitalhumanities

  13. [Veille] MOOC « Automatiser la reconnaissance de texte pour les SHS » : introduction à la reconnaissance automatique d’écriture appliquée aux documents historiques by @biblissima.bsky.social ; #CIHAMUMR5648 inside ! 25images.msh-lse.fr/portails/m
    #ATR #HTR #deeplearning #mooc #digitalhumanities

  14. [Veille] MOOC « Automatiser la reconnaissance de texte pour les SHS » : introduction à la reconnaissance automatique d’écriture appliquée aux documents historiques by @biblissima.bsky.social ; #CIHAMUMR5648 inside ! 25images.msh-lse.fr/portails/m
    #ATR #HTR #deeplearning #mooc #digitalhumanities

  15. These are primarily concerned with Handwritten Text Recognition (HTR), Natural Language Processing (NLP) and their application to premodern historical sources. Check out the official documentation to learn more about the software: docs.flow-project.net/latest/i (2/4) #ResearchSoftware #RSE #NLP #HTR

  16. These are primarily concerned with Handwritten Text Recognition (HTR), Natural Language Processing (NLP) and their application to premodern historical sources. Check out the official documentation to learn more about the software: docs.flow-project.net/latest/i (2/4) #ResearchSoftware #RSE #NLP #HTR

  17. After the opening by Lorella Viola yesterday, we start day 1 of our Summer University on “Doing migration history with digital methods” with two workshops: “From Scratch to Maps”, Giovanni Vitali introducing us to cartography, and Introduction to #HTR by Pauline Spychala and Hippolyte Souvay

    #migrationhistory #migration #GIS #digitalhistory #summeruniDHIP

  18. After the opening by Lorella Viola yesterday, we start day 1 of our Summer University on “Doing migration history with digital methods” with two workshops: “From Scratch to Maps”, Giovanni Vitali introducing us to cartography, and Introduction to #HTR by Pauline Spychala and Hippolyte Souvay

    #migrationhistory #migration #GIS #digitalhistory #summeruniDHIP

  19. After the opening by Lorella Viola yesterday, we start day 1 of our Summer University on “Doing migration history with digital methods” with two workshops: “From Scratch to Maps”, Giovanni Vitali introducing us to cartography, and Introduction to #HTR by Pauline Spychala and Hippolyte Souvay

    #migrationhistory #migration #GIS #digitalhistory #summeruniDHIP

  20. After the opening by Lorella Viola yesterday, we start day 1 of our Summer University on “Doing migration history with digital methods” with two workshops: “From Scratch to Maps”, Giovanni Vitali introducing us to cartography, and Introduction to #HTR by Pauline Spychala and Hippolyte Souvay

    #migrationhistory #migration #GIS #digitalhistory #summeruniDHIP

  21. After the opening by Lorella Viola yesterday, we start day 1 of our Summer University on “Doing migration history with digital methods” with two workshops: “From Scratch to Maps”, Giovanni Vitali introducing us to cartography, and Introduction to #HTR by Pauline Spychala and Hippolyte Souvay

    #migrationhistory #migration #GIS #digitalhistory #summeruniDHIP

  22. I'm teaching a class tomorrow on Arabic / Persian #HTR, and my example manuscript is absolutely amazing. It's a famous 16th-century work on mathematics by al-'Āmilī made in India and has an absolutely insane-looking layout - glosses going diagonally in several directions off the main text - that is nevertheless relatively clear to a human reader, and is not unusual in Arabic books. Will be interesting to see how an AI handles it!

    Library of Congress link: hdl.loc.gov/loc.wdl/wdl.9542 #palaeography

  23. I'm teaching a class tomorrow on Arabic / Persian #HTR, and my example manuscript is absolutely amazing. It's a famous 16th-century work on mathematics by al-'Āmilī made in India and has an absolutely insane-looking layout - glosses going diagonally in several directions off the main text - that is nevertheless relatively clear to a human reader, and is not unusual in Arabic books. Will be interesting to see how an AI handles it!

    Library of Congress link: hdl.loc.gov/loc.wdl/wdl.9542 #palaeography

  24. I'm teaching a class tomorrow on Arabic / Persian #HTR, and my example manuscript is absolutely amazing. It's a famous 16th-century work on mathematics by al-'Āmilī made in India and has an absolutely insane-looking layout - glosses going diagonally in several directions off the main text - that is nevertheless relatively clear to a human reader, and is not unusual in Arabic books. Will be interesting to see how an AI handles it!

    Library of Congress link: hdl.loc.gov/loc.wdl/wdl.9542 #palaeography

  25. I'm teaching a class tomorrow on Arabic / Persian #HTR, and my example manuscript is absolutely amazing. It's a famous 16th-century work on mathematics by al-'Āmilī made in India and has an absolutely insane-looking layout - glosses going diagonally in several directions off the main text - that is nevertheless relatively clear to a human reader, and is not unusual in Arabic books. Will be interesting to see how an AI handles it!

    Library of Congress link: hdl.loc.gov/loc.wdl/wdl.9542 #palaeography

  26. I'm teaching a class tomorrow on Arabic / Persian #HTR, and my example manuscript is absolutely amazing. It's a famous 16th-century work on mathematics by al-'Āmilī made in India and has an absolutely insane-looking layout - glosses going diagonally in several directions off the main text - that is nevertheless relatively clear to a human reader, and is not unusual in Arabic books. Will be interesting to see how an AI handles it!

    Library of Congress link: hdl.loc.gov/loc.wdl/wdl.9542 #palaeography

  27. En plus 💡 ateliers pratiques sur #OCR / #HTR, les SIG et le #traitement des #donnéesnumériques ainsi que des conférences plénières de Lorella Viola et Christoph Rass (@nghm_uos).
    En collaboration avec @c2dh.uni.lu, @Mareike2405 (IHA), Denis Scuto (C2DH), Machteld Venken (C2DH), Giovanni Vitali (UVSQ), Claire Zalc (@cnrs/ @ehess_fr ).

  28. En plus 💡 ateliers pratiques sur #OCR / #HTR, les SIG et le #traitement des #donnéesnumériques ainsi que des conférences plénières de Lorella Viola et Christoph Rass (@nghm_uos).
    En collaboration avec @c2dh.uni.lu, @Mareike2405 (IHA), Denis Scuto (C2DH), Machteld Venken (C2DH), Giovanni Vitali (UVSQ), Claire Zalc (@cnrs/ @ehess_fr ).

  29. En plus 💡 ateliers pratiques sur #OCR / #HTR, les SIG et le #traitement des #donnéesnumériques ainsi que des conférences plénières de Lorella Viola et Christoph Rass (@nghm_uos).
    En collaboration avec @c2dh.uni.lu, @Mareike2405 (IHA), Denis Scuto (C2DH), Machteld Venken (C2DH), Giovanni Vitali (UVSQ), Claire Zalc (@cnrs/ @ehess_fr ).

  30. En plus 💡 ateliers pratiques sur #OCR / #HTR, les SIG et le #traitement des #donnéesnumériques ainsi que des conférences plénières de Lorella Viola et Christoph Rass (@nghm_uos).
    En collaboration avec @c2dh.uni.lu, @Mareike2405 (IHA), Denis Scuto (C2DH), Machteld Venken (C2DH), Giovanni Vitali (UVSQ), Claire Zalc (@cnrs/ @ehess_fr ).

  31. En plus 💡 ateliers pratiques sur #OCR / #HTR, les SIG et le #traitement des #donnéesnumériques ainsi que des conférences plénières de Lorella Viola et Christoph Rass (@nghm_uos).
    En collaboration avec @c2dh.uni.lu, @Mareike2405 (IHA), Denis Scuto (C2DH), Machteld Venken (C2DH), Giovanni Vitali (UVSQ), Claire Zalc (@cnrs/ @ehess_fr ).

  32. Now the Swedish National Archives talking about their journey on making the archives more accessible using #htr and #ml #lion

  33. Now the Swedish National Archives talking about their journey on making the archives more accessible using #htr and #ml #lion

  34. Now the Swedish National Archives talking about their journey on making the archives more accessible using #htr and #ml #lion

  35. Now the Swedish National Archives talking about their journey on making the archives more accessible using #htr and #ml #lion

  36. Now the Swedish National Archives talking about their journey on making the archives more accessible using #htr and #ml #lion

  37. Objetivo: Manejar al menos una plataforma de #HTR (p. ej. #Transkribus o #eScriptorium): cargar documentos, lanzar reconocimiento, revisar y corregir resultados.
    Entender los conceptos básicos de entrenamiento de modelos: conjuntos de entrenamiento/validación, overfitting, tasas de error y #métricasdecalidad (CER/WER)
    Fomentar el trabajo interdisciplinar entre especialistas en humanidades, informática y #archivo / #biblioteca, articulando roles y tareas en proyectos colaborativos.

  38. Objetivo: Manejar al menos una plataforma de #HTR (p. ej. #Transkribus o #eScriptorium): cargar documentos, lanzar reconocimiento, revisar y corregir resultados.
    Entender los conceptos básicos de entrenamiento de modelos: conjuntos de entrenamiento/validación, overfitting, tasas de error y #métricasdecalidad (CER/WER)
    Fomentar el trabajo interdisciplinar entre especialistas en humanidades, informática y #archivo / #biblioteca, articulando roles y tareas en proyectos colaborativos.

  39. Objetivo: Manejar al menos una plataforma de #HTR (p. ej. #Transkribus o #eScriptorium): cargar documentos, lanzar reconocimiento, revisar y corregir resultados.
    Entender los conceptos básicos de entrenamiento de modelos: conjuntos de entrenamiento/validación, overfitting, tasas de error y #métricasdecalidad (CER/WER)
    Fomentar el trabajo interdisciplinar entre especialistas en humanidades, informática y #archivo / #biblioteca, articulando roles y tareas en proyectos colaborativos.

  40. Ponentes
    José Manuel Fradejas Rueda
    Catedrático Lengua Española #UniversidaddeValladolid
    Francisco Gago Jover
    Professor of Spanish, College of the Holy Cross (EEUU)
    Objetivos
    Comprender qué es el #HTR, en qué se diferencia del #OCR y en qué contextos resulta útil (patrimonio #archivosadministrativos, investigación, etc.)
    Conocer el ciclo completo de trabajo con HTR: obtención imágenes del manuscrito, exportación de transcripciones, y los diferentes tipos de formatos estructurados reutilizables.

  41. Ponentes
    José Manuel Fradejas Rueda
    Catedrático Lengua Española #UniversidaddeValladolid
    Francisco Gago Jover
    Professor of Spanish, College of the Holy Cross (EEUU)
    Objetivos
    Comprender qué es el #HTR, en qué se diferencia del #OCR y en qué contextos resulta útil (patrimonio #archivosadministrativos, investigación, etc.)
    Conocer el ciclo completo de trabajo con HTR: obtención imágenes del manuscrito, exportación de transcripciones, y los diferentes tipos de formatos estructurados reutilizables.

  42. Ponentes
    José Manuel Fradejas Rueda
    Catedrático Lengua Española #UniversidaddeValladolid
    Francisco Gago Jover
    Professor of Spanish, College of the Holy Cross (EEUU)
    Objetivos
    Comprender qué es el #HTR, en qué se diferencia del #OCR y en qué contextos resulta útil (patrimonio #archivosadministrativos, investigación, etc.)
    Conocer el ciclo completo de trabajo con HTR: obtención imágenes del manuscrito, exportación de transcripciones, y los diferentes tipos de formatos estructurados reutilizables.

  43. #HTR abre la puerta a proyectos de edición digital, corpus históricos y análisis lingüístico a gran escala, que antes eran inviables por el coste en tiempo de la transcripción manual. Para #archivosdeempresas y administraciones, la automatización de la lectura de documentos manuscritos incrementa de forma notable la productividad y reduce errores de entrada manual de datos. Entender las diferencias conceptuales y técnicas entre OCR tradicional y HTR neuronal

  44. #HTR abre la puerta a proyectos de edición digital, corpus históricos y análisis lingüístico a gran escala, que antes eran inviables por el coste en tiempo de la transcripción manual. Para #archivosdeempresas y administraciones, la automatización de la lectura de documentos manuscritos incrementa de forma notable la productividad y reduce errores de entrada manual de datos. Entender las diferencias conceptuales y técnicas entre OCR tradicional y HTR neuronal

  45. #HTR abre la puerta a proyectos de edición digital, corpus históricos y análisis lingüístico a gran escala, que antes eran inviables por el coste en tiempo de la transcripción manual. Para #archivosdeempresas y administraciones, la automatización de la lectura de documentos manuscritos incrementa de forma notable la productividad y reduce errores de entrada manual de datos. Entender las diferencias conceptuales y técnicas entre OCR tradicional y HTR neuronal

  46. I just updated my Greek Minuscule LLM HTR Benchmark and added the latest frontier models in addition to some open weight and other models.

    Some spoilers: Gemini is still far ahead for all metrics. Grok and Llama are about as bad as it gets.

    d-flood.github.io/paleo-bench/

    #DigitalHumanities #htr

  47. I just updated my Greek Minuscule LLM HTR Benchmark and added the latest frontier models in addition to some open weight and other models.

    Some spoilers: Gemini is still far ahead for all metrics. Grok and Llama are about as bad as it gets.

    d-flood.github.io/paleo-bench/

  48. I just updated my Greek Minuscule LLM HTR Benchmark and added the latest frontier models in addition to some open weight and other models.

    Some spoilers: Gemini is still far ahead for all metrics. Grok and Llama are about as bad as it gets.

    d-flood.github.io/paleo-bench/

    #DigitalHumanities #htr

  49. I just updated my Greek Minuscule LLM HTR Benchmark and added the latest frontier models in addition to some open weight and other models.

    Some spoilers: Gemini is still far ahead for all metrics. Grok and Llama are about as bad as it gets.

    d-flood.github.io/paleo-bench/

    #DigitalHumanities #htr

  50. I just updated my Greek Minuscule LLM HTR Benchmark and added the latest frontier models in addition to some open weight and other models.

    Some spoilers: Gemini is still far ahead for all metrics. Grok and Llama are about as bad as it gets.

    d-flood.github.io/paleo-bench/

    #DigitalHumanities #htr