Fine-tuning an LLM on text instructions converted to Whisper semantic tokens enables it to understand spoken instructions at inference, bypassing TTS and speech instruction data.
By lever- aging a quantized Whisper encoder, Speechless generates se- mantic speech tokens, effectively addressing challenges in low- resource languages
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Speechless: Speech Instruction Training Without Speech for Low Resource Languages
Fine-tuning an LLM on text instructions converted to Whisper semantic tokens enables it to understand spoken instructions at inference, bypassing TTS and speech instruction data.