TEA-ASR-1

Home/Models/JacobLinCool/TEA-ASR-1

JacobLinCool/TEA-ASR-1

kind: original
quant: bf16 (16-bit)
family: misc
modality: automatic-speech-recognition
root model: Qwen/Qwen3-ASR-1.7B
provider: JacobLinCool
license: mit
language: zh, en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 420
likes: 0
created: —
last modified: 2026-06-27T13:45:48+00:00 (2026)
huggingface: https://huggingface.co/JacobLinCool/TEA-ASR-1
tags: transformerssafetensorsqwen3_asrautomatic-speech-recognitiontaiwan-mandarintraditional-chinesecode-switchingqwen3-asrspeechzhenbase_model:Qwen/Qwen3-ASR-1.7Bbase_model:finetune:Qwen/Qwen3-ASR-1.7Blicense:mitendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
WER Common Voice	speech-asr	19.0		medium	`CommonVoice 19`
RTF	speech-asr	9.1		high	`\| TEA-ASR-1 \| 2B \| 11.0 \| 0.091 \| 4.16 \|`
WER Common Voice	speech-asr	3.64	CommonVoice 19 (zh-TW)	medium	`\| CommonVoice 19 (zh-TW) \| 3.64 \| 5.14 \| 3.90 \| 5.79 \| 8.03 \| 10.17 \|`

none scraped.