Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Lỗi với librosa ! #14

Open
trinhanhtuan opened this issue Aug 20, 2023 · 1 comment
Open

Lỗi với librosa ! #14

trinhanhtuan opened this issue Aug 20, 2023 · 1 comment

Comments

@trinhanhtuan
Copy link

Sau khi cài đặt, tôi chạy thử vào báo lỗi với librosa như ở dưới, tôi đang dùng librosa phiến bản 0.10.1

Cảm ơn bạn,
Tuấn

root@voice-dev-01:/opt/viet-asr# python3 infer.py audio_samples
################################################################################

WARNING, path does not exist: KALDI_ROOT=/mnt/matylda5/iveselyk/Tools/kaldi-trunk

(please add 'export KALDI_ROOT=<your_path>' in your $HOME/.profile)

(or run as: KALDI_ROOT=<your_path> python <your_script>.py)

################################################################################

2023-08-20 08:26:24.098 | INFO | main::179 - transcribe audio file in : audio_samples
2023-08-20 08:26:24.098 | INFO | main:init:74 - Init VietASR with params:
2023-08-20 08:26:24.098 | INFO | main:init:75 - ========================
2023-08-20 08:26:24.098 | INFO | main:init:76 - + config: configs/quartznet12x1_vi.yaml
2023-08-20 08:26:24.098 | INFO | main:init:77 - + encoder_checkpoint: models/acoustic_model/vietnamese/JasperEncoder-STEP-289936.pt
2023-08-20 08:26:24.098 | INFO | main:init:78 - + decoder_checkpoint: models/acoustic_model/vietnamese/JasperDecoderForCTC-STEP-289936.pt
2023-08-20 08:26:24.098 | INFO | main:init:79 - + lm_path: models/language_model/3-gram-lm.binary
2023-08-20 08:26:24.098 | INFO | main:init:80 - + lm_alpha: 0.5
2023-08-20 08:26:24.098 | INFO | main:init:81 - + lm_beta: 1.5
2023-08-20 08:26:24.098 | INFO | main:init:82 - + device: cpu
2023-08-20 08:26:24.098 | INFO | main:init:83 - ========================
[NeMo I 2023-08-20 08:26:24 features:149] PADDING: 0
[NeMo I 2023-08-20 08:26:24 features:170] STFT using torch
Traceback (most recent call last):
File "/opt/viet-asr/infer.py", line 186, in
vietasr = VietASR(
File "/opt/viet-asr/infer.py", line 102, in init
data_preprocessor = nemo_asr.AudioToMelSpectrogramPreprocessor(
File "/opt/viet-asr/nemo/collections/asr/audio_preprocessing.py", line 352, in init
self.featurizer = FilterbankFeatures(
File "/opt/viet-asr/nemo/collections/asr/parts/features.py", line 200, in init
librosa.filters.mel(sample_rate, self.n_fft, n_mels=nfilt, fmin=lowfreq, fmax=highfreq,),
TypeError: mel() takes 0 positional arguments but 2 positional arguments (and 3 keyword-only arguments) were given

root@voice-dev-01:/opt/viet-asr# pip3 list | grep librosa
librosa 0.10.1

@trinhanhtuan trinhanhtuan changed the title L Lỗi với librosa ! Aug 20, 2023
@dangvansam
Copy link
Owner

Bạn cài librosa 0.7.2 xem sao

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants