{"id":9817,"date":"2026-10-05T01:09:04","date_gmt":"2026-10-04T16:09:04","guid":{"rendered":"https:\/\/localmodelwatch.tsuchitsuchi.com\/2026\/10\/05\/diarizationlm-gemma-4-e4b-v1\/"},"modified":"2026-10-05T01:09:04","modified_gmt":"2026-10-04T16:09:04","slug":"diarizationlm-gemma-4-e4b-v1","status":"publish","type":"post","link":"https:\/\/localmodelwatch.tsuchitsuchi.com\/en\/2026\/10\/05\/diarizationlm-gemma-4-e4b-v1\/","title":{"rendered":"DiarizationLM-Gemma-4-E4B-v1 Vision-Language Model: 8GB+ VRAM"},"content":{"rendered":"

<\/p>\n

At a Glance<\/h2>\n
\n\n\n\n\n\n\n\n\n\n\n\n
Item<\/th>\nValue<\/th>\n<\/tr>\n<\/thead>\n
Repository<\/td>\ngoogle\/DiarizationLM-Gemma-4-E4B-v1<\/a><\/td>\n<\/tr>\n
Publisher guide<\/td>\nGoogle: models and licenses<\/a><\/td>\n<\/tr>\n
Published<\/td>\n2026-10-04<\/td>\n<\/tr>\n
License<\/td>\napache-2.0<\/td>\n<\/tr>\n
Formats<\/td>\nGGUF<\/a> \/ safetensors<\/a><\/td>\n<\/tr>\n
Paper<\/td>\narXiv:2401.03506<\/a><\/td>\n<\/tr>\n
Source type<\/td>\nPrimary source (the publisher itself)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div>\n

Values determined by this site’s code when the information was collected. Dates are JST.<\/em><\/p>\n

<\/p>\n

Overview<\/h2>\n

Google has released “DiarizationLM-Gemma-4-E4B-v1”, a large language model designed for speech processing. This model is based on Google’s “Gemma 4 E4B” and was fine-tuned using the Locality-Preserving Oracle Supervision method. Note that it is explicitly specified as not being an officially supported Google product.<\/p>\n

This model takes text output from automatic speech recognition (ASR) and speaker diarization systems, post-processes and corrects turn boundaries and backchannel errors, and outputs optimized text with speaker labels. Unlike traditional models specialized for two-speaker telephone audio, a key feature is that it is optimized across four standard corpora including multi-speaker (up to 9 people) meeting datasets.<\/p>\n

Specifications<\/h2>\n

The published specifications and training conditions are as follows:<\/p>\n