HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

stt_tl_fastconformer_hybrid_large

NCSpeech/stt_tl_fastconformer_hybrid_large

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
—
provider
NCSpeech
license
cc-by-4.0
language
tl, fil
context
—
library
nemo
vRAM (GB)
—
size on disk
—
downloads
168
likes
1
created
—
last modified
2025-10-26T22:43:52+00:00 (2025)
huggingface
https://huggingface.co/NCSpeech/stt_tl_fastconformer_hybrid_large
tags
nemoasrautomatic-speech-recognitionfastconformertagalogfilipinospeechtlfildataset:google/fleursarxiv:2305.05084license:cc-by-4.0model-indexregion:us

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WER FLEURSspeech-asr9.34low| 1 | **FastConformer-Hybrid Large**(our) | 115M | 9.34% | **16.10%** |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.