Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Pronunciation Training Feedback Generation on L2-Arctic-plus Human Evaluation (12 samples)
Loading...
3.8
SR (Suggestion Relevance)
Whisper Large + Llama-3.1-8B
1.72
2.26
2.8
3.34
Jan 21, 2026
SR (Suggestion Relevance)
UU (User Understandability)
OE (Overall Evaluation)
Updated 1mo ago
Evaluation Results
Method
Method
Links
SR (Suggestion Relevance)
UU (User Understandability)
OE (Overall Evaluation)
Whisper Large + Llama-3.1-8B
Framework=Instruction-...
2026.01
3.8
3.81
3.73
GPT-4o-Audio
2026.01
2.88
3.51
3.07
Qwen2-Audio
2026.01
2.12
2.83
2.26
Wav2vec2 Base + Llama-3.1-8B
Framework=ASR+LLM casc...
2026.01
1.8
2.5
1.9
Feedback
Search any
task
Search any
task