Leng2beat

speech-quality-assessement-qwen2audio-sft-temporal-full-h100

Greedy inference on the temporal test sets:

Table with columns: Test set, Samples, Parse rate, Mean t-IoU, Median t-IoU, Hit@0.1, Hit@0.3, Hit@0.5
Test set	Samples	Parse rate	Mean t-IoU	Median t-IoU	Hit@0.1	Hit@0.3	Hit@0.5
FOR	240	1.0000	0.2147	0.0575	0.4792	0.3708	0.1625
LIVE	200	1.0000	0.1261	0.0000	0.2750	0.1850	0.1150
P501	240	1.0000	0.2220	0.0000	0.4458	0.3333

Evaluation outputs were produced under: results/evaluation/temporal/sft_temporal_full_h100_tests.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Model Details

Model Provider

Leng2beat

Model Tree

Base

Qwen/Qwen2-Audio-7B

Fine-tuned

this model

Input Modalities

TextAudio

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Greedy inference on the temporal test sets:

Table with columns: Test set, Samples, Parse rate, Mean t-IoU, Median t-IoU, Hit@0.1, Hit@0.3, Hit@0.5
Test set	Samples	Parse rate	Mean t-IoU	Median t-IoU	Hit@0.1	Hit@0.3	Hit@0.5
FOR	240	1.0000	0.2147	0.0575	0.4792	0.3708	0.1625
LIVE	200	1.0000	0.1261	0.0000	0.2750	0.1850	0.1150
P501	240	1.0000	0.2220	0.0000	0.4458	0.3333

Evaluation outputs were produced under: results/evaluation/temporal/sft_temporal_full_h100_tests.