HF Model & Benchmark Matrix

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

chunkformer-ctc-large-vie

khanhld/chunkformer-ctc-large-vie

kind
original
quant
bf16 (16-bit)
family
misc
modality
automatic-speech-recognition
root model
—
provider
khanhld
license
cc-by-nc-4.0
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
599
likes
35
created
—
last modified
2025-10-08T08:02:13+00:00 (2025)
huggingface
https://huggingface.co/khanhld/chunkformer-ctc-large-vie
tags
pytorchtranscriptionaudiospeechchunkformerasrautomatic-speech-recognitionviedataset:legacy-datasets/common_voicedataset:vlsp2020_vinai_100hdataset:AILAB-VNUHCM/vivosdataset:doof-ferb/vlsp2020_vinai_100hdataset:doof-ferb/fpt_fosddataset:doof-ferb/infore1_25hoursdataset:linhtran92/viet_bud500dataset:doof-ferb/LSVSCdataset:doof-ferb/vais1000dataset:doof-ferb/VietMed_labeleddataset:NhutP/VSV-1100dataset:doof-ferb/Speech-MASSIVE_viedataset:doof-ferb/BibleMMS_viedataset:capleaf/viVoicearxiv:2502.14673license:cc-by-nc-4.0

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
WER Common Voicespeech-asr6.66low| 1 | **ChunkFormer** | 110M | 4.18 | 6.66 | 14.09 | **8.31** |

Discussions (0)

none scraped.

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