Pinned native speech-recognition models. Downloads are immutable; verify their size and SHA-256 before use. Retain the linked licenses and attribution when redistributing.
parakeet-tdt-0.6b-v3-Q8_0.gguf (739,508,576 bytes)
SHA-256: 5859f77944efcd8eafa23a6350731960b2b55b2203df51f319665c807d802cc7
Base model by NVIDIA. GGUF conversion and Q8_0 quantization by handy-computer. Boo mirrors these weights without further changes.
CC-BY-4.0 | Attribution and notices | Retained model card | Pinned upstream weights
whisper-large-v3-turbo-Q8_0.gguf (886,381,824 bytes)
SHA-256: d5e65f2b0828802ae2c231673d31982cebe3a778c95d9494a9f3efee6bd17448
Base model by OpenAI. GGUF conversion and Q8_0 quantization by handy-computer. Boo mirrors these weights without further changes.
Apache-2.0 (conversion); MIT (OpenAI base model) | Attribution and notices | Retained model card | Pinned upstream weights
parakeet-tdt-0.6b-v3-Q4_K_M.gguf (485,425,504 bytes)
SHA-256: b68557be1e3c40207fd7c4bd9d63f1d3316b963f15325bfb0cc16a8bb0ffd181
Base model by NVIDIA. GGUF conversion and Q4_K_M quantization by handy-computer. Boo mirrors these weights without further changes.
CC-BY-4.0 | Attribution and notices | Retained model card | Pinned upstream weights
parakeet-tdt-0.6b-v3-Q5_K_M.gguf (548,946,272 bytes)
SHA-256: cc722e76adc1a629fc0b2535de879d99b8160d07ad4c0215e2ca7d7ea0ae4b8f
Base model by NVIDIA. GGUF conversion and Q5_K_M quantization by handy-computer. Boo mirrors these weights without further changes.
CC-BY-4.0 | Attribution and notices | Retained model card | Pinned upstream weights
parakeet-tdt-0.6b-v3-Q6_K.gguf (610,342,240 bytes)
SHA-256: ab1bbcbe3e1c4c2ec12ca1df1aeafd22e9043ce7262e4b5f5c5d7d76418a9ae8
Base model by NVIDIA. GGUF conversion and Q6_K quantization by handy-computer. Boo mirrors these weights without further changes.
CC-BY-4.0 | Attribution and notices | Retained model card | Pinned upstream weights