Press Space to continue
Fine-tuned model tops 8 Vietnamese ASR benchmarks in 3 hours
Press Space to continue
The community has already been fine-tuning EmbeddingGemma 2 and getting great results! With just 3 hours of training on 3,000 hours of Vietnamese audio, it tops 8 Vietnamese ASR benchmarks. All without needing a heavy autoregressive decoder.
open on x · 3 viewsViews and clicks count once per visitor per day. Clicks are opens of this post on X.