Repository: localaiLicense: apache-2.0
Omnilingual ASR CTC 300M (int8) is a multilingual automatic speech recognition model supporting 1,600+ languages. Based on Meta's omniASR_CTC_300M architecture (Wav2Vec2 with CTC head), quantized to int8 for efficient inference. Uses the sherpa-onnx backend with ONNX Runtime.
Links
Tags
Repository: localaiLicense: apache-2.0
Streaming English ASR: sherpa-onnx zipformer transducer (int8, chunk-16 left-128). Low-latency real-time transcription with endpoint detection via sherpa-onnx's online recognizer. English-only; for multilingual offline ASR see omnilingual-0.3b-ctc-q8-sherpa.
Links
Tags
Hybrid TDT+CTC FastConformer, 110M. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
CTC FastConformer, 0.6B. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
CTC FastConformer, 1.1B. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
Hybrid TDT+CTC FastConformer, 1.1B. F16 GGUF for the parakeet-cpp backend (C++/ggml port of NVIDIA NeMo Parakeet), byte-identical to NeMo at WER 0. Faster than NeMo on CPU and GPU.
Links
Tags
NVIDIA Parakeet hybrid TDT+CTC 110M (smallest, CTC decode), English-only ASR. Runs via the CrispASR backend. Default GGUF size ~91 MB.
Links
Tags
NVIDIA Parakeet hybrid TDT+CTC 1.1B (multilingual, casing + punctuation) ASR. Runs via the CrispASR backend. Default GGUF size ~810 MB.
Links
Tags
NVIDIA STT-EN FastConformer-CTC Large, English ASR. Runs via the CrispASR backend. Default GGUF size ~83 MB.
Links
Tags