Model Adaptation to upweight individual word probability
未关闭
- 主要语言
- Jupyter Notebook
- 星标
- 15.1k
- 派生
- 1.8k
- PR 合并指标
- 30 天内没有已合并 PR
描述
The code in `KaldiRecognizer::KaldiRecognizer(Model *model, float sample_frequency, char const *grammar)` makes an entirely new `g_fst`. Is there instead a way to upweight the probability of a single word in `model_->g_fst_` easily while keeping the acceptor/decoding graph of a model?
贡献指南
这个仓库没有索引到贡献指南
评估
这个 Issue 还没有评估数据。