Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Token-level Predictability on LibriSpeech 100
Loading...
8.44
Eval Loss
LLM-CODEC
8.2984
9.2542
10.21
11.1658
Apr 20, 2026
Eval Loss
Perplexity
Updated 1mo ago
Evaluation Results
Method
Method
Links
Eval Loss
Perplexity
LLM-CODEC
2026.04
8.44
4,617
WavTok-L
2026.04
11.91
148,122
UniCodec
2026.04
11.92
150,197
BigCodec
2026.04
11.96
156,448
AUV
2026.04
11.98
159,768
Feedback
Search any
task
Search any
task