In an ASR context where most phenomena have been studied for more widespread languages, the present work seeks to propose a solution for code-switching, a phenomenon whereby a multilingual speaker alternates between the different languages they master throughout their speech, in intersentential contexts where the speaker switches languages between sentences, typically due to syntactic differences among the languages they speak.<\/span><\/p>\n To this end, the fine-tuning of Whisper, a technology widely used for audio transcription, is proposed in order to deeply train its models on the different languages involved in the speaker\u2019s code-switching phenomenon, and to create an architecture that enables reinforced transcription for languages with less coverage.<\/span><\/p>\n This architecture begins with two blocks that properly process the audio in order to maximize accuracy in each of its segments: a VAD block, using Silero VAD, to divide the audio into segments where speech activity is present; followed by an LID block, which aims to identify the language of each of these audio segments in order to perform a transcription adapted to the corresponding language. <\/span><\/p>\n Once the segments have been divided and labeled by language, a specific transcription for Basque is carried out using a fine-tuned Whisper model, while the base model is retained for Spanish (since it already has sufficient coverage). The transcriptions of each segment are then combined into a final text file.<\/span><\/p>\n All of this is carried out based on two datasets: one for fine-tuning, obtained from the Mozilla Common Voice platform, and a second one for architecture validation, which is synthetic and contains code-switched audio samples that follow the intersentential structure addressed in this work.<\/span><\/p>\n <\/p>[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”4.18.0″ _module_preset=”default” custom_margin=”20px||||false|false” custom_padding=”0px||||false|false” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_row column_structure=”1_2,1_2″ _builder_version=”4.25.1″ _module_preset=”default” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_column type=”1_2″ _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_image src=”https:\/\/storage.googleapis.com\/wp-uploads.bucket.wp.uc3m.es\/wp-content\/uploads\/sites\/70\/2026\/05\/19111753\/Foto.jpeg” title_text=”Foto” _builder_version=”4.27.6″ _module_preset=”default” hover_enabled=”0″ global_colors_info=”{}” theme_builder_area=”post_content” sticky_enabled=”0″][\/et_pb_image][\/et_pb_column][et_pb_column type=”1_2″ _builder_version=”4.18.0″ _module_preset=”default” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_text _builder_version=”4.27.6″ _module_preset=”default” custom_padding=”||0px|||” hover_enabled=”0″ global_colors_info=”{}” theme_builder_area=”post_content” sticky_enabled=”0″] BACHELOR’S THESIS BY<\/strong><\/span><\/p>\n JAVIER RAM\u00cdREZ ZARZOSO<\/b><\/span><\/p>[\/et_pb_text][et_pb_text _builder_version=”4.25.1″ _module_preset=”default” global_colors_info=”{}” theme_builder_area=”post_content”] <\/strong><\/p>\n <\/strong><\/p>\n <\/strong><\/p>\n Academic experience<\/strong><\/p>\n <\/p>[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=”4.20.2″ _module_preset=”default” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_column type=”4_4″ _builder_version=”4.20.2″ _module_preset=”default” global_colors_info=”{}” theme_builder_area=”post_content”][et_pb_text _builder_version=”4.25.1″ _module_preset=”default” custom_padding=”||9px|||” global_colors_info=”{}” theme_builder_area=”post_content”] Work experience<\/strong><\/p>\n\n
<\/ul>\n
\n
Skills<\/strong><\/p>\n\n
\n