Home/Models/nvidia/stt_en_fastconformer_hybrid_large_streaming_multi
stt_en_fastconformer_hybrid_large_streaming_multi
nvidia/stt_en_fastconformer_hybrid_large_streaming_multi
- kind
- original
- quant
- bf16 (16-bit)
- family
- misc
- modality
- automatic-speech-recognition
- root model
- nvidia/stt_en_fastconformer_hybrid_large_streaming_multi
- provider
- nvidia
- license
- cc-by-4.0
- language
- en
- context
- —
- library
- nemo
- vRAM (GB)
- —
- size on disk
- —
- downloads
- 1,048
- likes
- 27
- created
- —
- last modified
- 2025-02-18T13:28:17+00:00 (2025)
- huggingface
- https://huggingface.co/nvidia/stt_en_fastconformer_hybrid_large_streaming_multi
- tags
- nemoautomatic-speech-recognitionspeechstreamingaudioTransducerConformerCTCpytorchNeMoendataset:librispeech_asrdataset:fisher_corpusdataset:Switchboard-1dataset:WSJ-0dataset:WSJ-1dataset:National-Singapore-Corpus-Part-1dataset:National-Singapore-Corpus-Part-6dataset:vctkdataset:VoxPopuli-ENdataset:Europarl-ASR-ENdataset:Multilingual-LibriSpeech-2000hoursdataset:mozilla-foundation/common_voice_8_0dataset:MLCommons/peoples_speech
Benchmark scores (0)
no scores extracted for this variant.
Discussions (0)
none scraped.