BSC_IWSLT26_IF_SHORT_unconstrained_contrastive1
Data conditions: unconstrained
Model architecture: direct (mhubert-base-25hz speech encoder and SalamandraTA-7B-wmt25 as the LLM backbone)
Model architecture: direct (mhubert-base-25hz speech encoder and SalamandraTA-7B-wmt25 as the LLM backbone)
| From\To | de | en | it | zh |
|---|---|---|---|---|
| en | N/A | N/A | N/A | N/A |