Open ghost opened 4 years ago
Hello guys. I tried to use language model for inference. I've successfully built custom tensorflow (https://nvidia.github.io/OpenSeq2Seq/html/installation.html#how-to-build-a-custom-native-tf-op-for-ctc-decoder-with-language-model-optional). But after it, when I try to run ./scripts/download_lm.sh, it gives
./scripts/download_lm.sh
Reading 4-gram-lower.arpa ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100 Identifying n-grams omitted by SRI ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100 Quantizing ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100 Writing trie ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100 SUCCESS INFO: Skipping trie generation, since no custom TF op based CTC decoder found. INFO: Please use Baidu CTC decoder with this language model.
Reading 4-gram-lower.arpa ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
Identifying n-grams omitted by SRI ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
Quantizing ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
Writing trie ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100
SUCCESS INFO: Skipping trie generation, since no custom TF op based CTC decoder found. INFO: Please use Baidu CTC decoder with this language model.
How can I build language model?
Hello guys. I tried to use language model for inference. I've successfully built custom tensorflow (https://nvidia.github.io/OpenSeq2Seq/html/installation.html#how-to-build-a-custom-native-tf-op-for-ctc-decoder-with-language-model-optional). But after it, when I try to run
./scripts/download_lm.sh
, it givesHow can I build language model?