RinggAI/Transcript-Analytics-SLM1.5b

RinggAI/Transcript-Analytics-SLM1.5b is a 1.5 billion parameter instruction-tuned language model developed by RinggAI, fine-tuned from unsloth/Qwen2.5-1.5B-Instruct. It is specifically designed for analyzing call transcripts in Hindi, English, and mixed Hinglish, including noisy audio. The model excels at extracting enum-based classifications, conversation summaries, and action items from real-world call data, with a context length of 131072 tokens.