Unverified50% confidenceFactExact time
Cactus Compute launched the Whistle speech model, with a size of 16.9 MB.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhisper Base remains a reliable baseline for general transcription, especially in multilingual, complex acoustic environments; Cactus Whistle, meanwhile, pushes the threshold of speech recognition down to a new order of magnitude in size.70% similarUnverifiedWhisper Tiny 仅有39M参数，语音模型可经INT8/INT4量化后部署于手机SoC和嵌入式芯片（如树莓派、NVIDIA Jetson）67% similarUnverifiedWhen running needle-whistle-playground for the first time, if a microphone is used, additional dependencies must be installed, added via uv add cactus-needle[mic].65% similarUnverifiedWhisper offers multiple sizes from tiny to large, with parameter counts ranging from about 39 million to 1.55 billion, is highly robust to differences in accent, background noise and recording quality, and supports language identification and translation.63% similarUnverifiedVoxtral uses a 3-billion-parameter text model as its backbone and converts audio into continuous embeddings via an audio encoder that are fed directly into the decoder, which differs from Whisper's approach of feeding into the decoder via cross-attention.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084473API
curl https://kongchang.com/api/v1/knowledge/claims/1084473MCP
get_claim(id=1084473)