-
-
-
cc @ezyang @msaroufim @wconstab @bdhirsh @anijain2305
-
Hi, I'm running into this problem.
`python3 blstm_model_run.py --input features.arff --output results.arff --model data/models --feat speed direction`
`Traceback (most recent call last):
File…
-
So like model could be served as an API model or locally?
-
We have been developing (enhancing) speech enhancement functions in ESPnet2.
We particularly design it to tightly integrate it with downstream speech processing tasks (I.e., ASR and ST).
Phase 1 is…
-
v0.3.1 is only compatible with v2.6.3 of CUDA.jl (currently on v3.5.0). This breaks audio processing projects that want to use it with the latest version of Flux (which uses the latest CUDA.jl).
-
-
```
2021-12-28T14:44:45 (tts.sh:205:main) ./tts.sh --lang en --feats_type raw --fs 22050 --n_fft 1024 --n_shift 256 --token_type phn --cleaner none --g2p none --train_config conf/train.yaml --inferen…
-
打扰您了，请问重构HSA_BLSTM的时候，对content和comment是如何处理的？即如何获得con_embedding_matrix和com_embedding_matrix，另外con_steps和com_steps这个是具体设置的值还是通过计算得到的呢？谢谢您。