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.
Datasets For Stage 1, we utilized two automatic speech recognition (ASR) datasets: viV oice (Vietnamese) and LibriTTS-R[22] (English)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 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.