Anjul Rajendra Sharma

I'm also installing eesen latest version but facing same problem: collect2: error: ld returned 1 exit status ../makefiles/default_rules.mk:35: recipe for target 'liblm.so' failed make[1]: *** [liblm.so] Error 1 make[1]: Leaving...

Hi, I'm facing the same issue with the default conformer config(changed min_duration=1.6 and max_duration=30.0). ``` File "/usr/local/lib/python3.10/dist-packages/pytorch_lightning/loops/batch/training_batch_loop.py", line 88, in advance outputs = self.optimizer_loop.run(optimizers, kwargs) File "/usr/local/lib/python3.10/dist-packages/pytorch_lightning/loops/loop.py", line 199, in...

Hi @yuekaizhang , i have tried to use add LM with triton decoder, it loads successfully but got no o/p or weird o/p. I have tried 2 types of LM:...

Hi, Sharing Results from both LM. I have trained hindi model, and tried space_id =-1 as well but didn't work. **without LM** - working well Took:1.472s Get response from 1th...

Hi @yuekaizhang, default value of space_id was -1 only if space is not on the symbol table. https://github.com/wenet-e2e/wenet/blob/main/runtime/gpu/model_repo_stateful/wenet/1/wenet_onnx_model.py#L34 my words.txt file format: ``` 0 1 अ 2 अँकल 3 अँकी...

@yuekaizhang, I have used bpe units while training. I have tried using same bpe units with word LM and bpe tokenized LM with space_id=-1 but no luck, later i have...

Hi @yuekaizhang, can you please suggest how to fix it?

graph build successfully and memory location got updated. 

Hi @pengzhendong i have tried the other approach to, i have added a new method `void ContextGraph::UpdateContextGraph(std::string on_request_context_words_, float on_request_context_score_, const std::shared_ptr& unit_table)` in `context_graph.h` header file, which can be...

i have define it in cc file, now it's working as expected. thanks