-
Error occurred when executing WhisperX:
TranscriptionOptions.__new__() missing 1 required positional argument: 'hotwords'
-
I tried the following diff:
```diff
diff --git a/integration_tests/intrinsics_45.f90 b/integration_tests/intrinsics_45.f90
index 3c537aacc..90c93af12 100644
--- a/integration_tests/intrinsics_45.f…
-
Here is my running command:'
```python
CUDA_VISIBLE_DEVICES=0,1 python -m torch.distributed.launch --nproc_per_node=2 train_with_wav2vect.py hparams/train_ASR_transformer_with_wav2vect.yaml --data_f…
-
We are now actively developing VERSA for general-purpose speech/audio evaluation.
- Additional Metrics to add
- [x] torch-squim (metrics done, pending adding to the interface) https://pytorch.or…
-
The radiation processes have three separate input parameters
- `S0`
- `insolation`
- `coszen`
Currently, if `coszen` is omitted then it gets assigned an [inferred default value](https://github.c…
-
Dear everyone,
I trained two E2E models with espnet and wonder if it is feasible to make joint inferences, which means using both models' knowledge for inference. If so, how to implement it? Many t…
-
Testing:
- [x] Windows 1578
- [x] Windows 1432
- [x] Windows 1221
- [x] Windows 1028
- [x] Linux 1578
- [x] Linux 1432
- [x] Linux 1221
- [ ] Linux 1028
- [x] Mac 1578
- [ ] Mac 1432
- [x] …
-
run.sh: line 186: 9762 Segmentation fault (core dumped) CUDA_VISIBLE_DEVICES=${gpu} ${NEURALSP_ROOT}/neural_sp/bin/asr/train.py --corpus aishell1 --config ${conf} --config2 ${conf2} --n_gpus ${n…
-
There are several issues that we need to think about.
# Underscore in variables
Automatically generated variables in ASR often look like `__1_t` and on purpose contain characters that are not va…
-
您好，非常感谢昨天的问题解答。想再请教一下语音识别阶段怎么换成GPU的，感觉CPU还是偏慢，实用有些受局限。