Comments (4)
To give extra report. To avoid ZeroDivisionError shown above, I modified the code in speechbrain/utils/data_utils.py as follows:
in func pad_right_to()
from:
valid_vals.append(tensor.shape[j] / target_shape[j])
to:
if target_shape[j] != 0:
valid_vals.append(tensor.shape[j] / target_shape[j])
else:
valid_vals.append(1.0)
So it looks like the following:
After the such a modification and given a new batchsize of 8, the training process went on well and finished one epoch as following:
However, before going any further, it reported an error "sentencepiece_processor.cc(954) LOG(ERROR) src/sentencepiece_processor.cc(294) [model_] Model is not initialized."
And throwed an exception as follows:
Back to the frame of compute_objectives(), the information is as follows:
from speechbrain.
This problem was caused by my mistake.
from speechbrain.
I am also experiencing the same problem.
How did you solve this problem?
from speechbrain.
Sorry to see your comment until now.
My problem is caused because my mistake that I commented the initialization codes of the pretrainer. As shown in the red box of the following figure, I commented them and got the zerodivision error. Besides, I didn't give the correct configure args for pretrainer section in train.yaml .
from speechbrain.
Related Issues (20)
- VAD - very slow "apply_threshold" when running on cuda device + possible solution HOT 1
- Invalid file: WindowsPath('audio_cache/1min.mp3') HOT 1
- Unable to perform pretraining of Wav2vec2
- Release tarball contains a top level tests package HOT 1
- Declaration: torchaudio_sox::load_audio_file(str _0, int? _1, int? _2, bool? _3, bool? _4, str? _5) -> (Tensor _0, int _1) Cast error details: Unable to cast Python instance of type <class 'pathlib.PosixPath'> to C++ type '?' (#define PYBIND11_DETAILED_ERROR_MESSAGES or compile in debug mode for details) HOT 1
- How do you add a yaml file? HOT 2
- ZeroDivisionError: division by zero HOT 7
- URL checks: false positives, filtering and fixes to do
- soundchoice-g2p on HF emits `<eos>` symbol (which HF tests don't expect)
- v1.0.1 docs are failing HOT 4
- Github release actions failing
- SpeechBrain pipelines
- SpeechBrain and ONNX HOT 2
- DDP backend enhancement
- SpeechLLM and Whisper HOT 6
- Speechbrain reference name of V1 too long
- ASR Model Trained with Orange/SSA-HuBERT-base-60k Returns Empty String During Inference HOT 11
- Is there a reference to the noise file used in the Voxlingua107 train_ecapa receipe? HOT 1
- large CER HOT 5
- Move tutorials to main repository
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from speechbrain.