tamil-asr-qwen3

Home/Models/osmapi/tamil-asr-qwen3

osmapi/tamil-asr-qwen3

kind: original
quant: bf16 (16-bit)
family: qwen
modality: automatic-speech-recognition
root model: Qwen/Qwen3-ASR-1.7B
provider: osmapi
license: apache-2.0
language: ta
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 197
likes: 2
created: —
last modified: 2026-07-01T15:45:23+00:00 (2026)
huggingface: https://huggingface.co/osmapi/tamil-asr-qwen3
tags: transformerssafetensorsqwen3_asrautomatic-speech-recognitiontamiltamil-asrasrspeech-to-textsttspeech-recognitionindicdravidianindiaqwen3-asrfleurstadataset:google/fleursdataset:ai4bharat/indicvoicesdataset:ai4bharat/Shrutilipidataset:ai4bharat/kathbathbase_model:Qwen/Qwen3-ASR-1.7Bbase_model:finetune:Qwen/Qwen3-ASR-1.7Blicense:apache-2.0model-index

benchmark	category	score	context	conf	evidence
WER	speech-asr	25.27		low	`\| Tamil-ASR-Qwen3 (this model) \| 25.27% \| 7.95% \|`
CER	speech-asr	7.95		low	`\| Tamil-ASR-Qwen3 (this model) \| 25.27% \| 7.95% \|`

none scraped.