bene-ges

/

ru_g2p_ipa_bert_large

like 4

Hello! I'm trying to reproduce your results, and getting the error while executing nemo/examples/nlp/text_normalization_as_tagging/normalization_as_tagging_infer.py from your notebook Russian_TTS_with_IPA_G2P_FastPitch_and_HifiGAN.ipynb

[NeMo W 2024-11-07 12:51:27 nemo_logging:361] /usr/local/lib/python3.10/dist-packages/pydub/utils.py:170: RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work
warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning)

[NeMo W 2024-11-07 12:51:27 nemo_logging:361] /usr/local/lib/python3.10/dist-packages/hydra/_internal/hydra.py:119: UserWarning: Future Hydra versions will no longer change working directory at job runtime by default.
See https://hydra.cc/docs/1.2/upgrades/1.1_to_1.2/changes_to_job_working_dir/ for more information.
ret = run_job(

GPU available: True (cuda), used: True
TPU available: False, using: 0 TPU cores
HPU available: False, using: 0 HPUs
Trainer(val_check_interval=1.0) was configured so validation will run at the end of the training epoch..
[NeMo I 2024-11-07 12:51:27 helpers:63] Loading pretrained model ru_g2p_ipa_bert_large/ru_g2p.nemo
Error executing job with overrides: ['pretrained_model=ru_g2p_ipa_bert_large/ru_g2p.nemo', 'inference.from_file=input_for_g2p.txt', 'inference.out_file=output_of_g2p.txt', 'model.max_sequence_len=512', 'inference.batch_size=128', 'lang=ru']
Traceback (most recent call last):
File "/nemo_compatible/notebooks/nemo/examples/nlp/text_normalization_as_tagging/normalization_as_tagging_infer.py", line 91, in
main()
File "/usr/local/lib/python3.10/dist-packages/nemo/core/config/hydra_runner.py", line 129, in wrapper
_run_hydra(
File "/usr/local/lib/python3.10/dist-packages/hydra/_internal/utils.py", line 394, in _run_hydra
_run_app(
File "/usr/local/lib/python3.10/dist-packages/hydra/_internal/utils.py", line 457, in _run_app
run_and_report(
File "/usr/local/lib/python3.10/dist-packages/hydra/_internal/utils.py", line 223, in run_and_report
raise ex
File "/usr/local/lib/python3.10/dist-packages/hydra/_internal/utils.py", line 220, in run_and_report
return func()
File "/usr/local/lib/python3.10/dist-packages/hydra/_internal/utils.py", line 458, in
lambda: hydra.run(
File "/usr/local/lib/python3.10/dist-packages/hydra/_internal/hydra.py", line 132, in run
_ = ret.return_value
File "/usr/local/lib/python3.10/dist-packages/hydra/core/utils.py", line 260, in return_value
raise self._return_value
File "/usr/local/lib/python3.10/dist-packages/hydra/core/utils.py", line 186, in run_job
ret.return_value = task_function(task_cfg)
File "/nemo_compatible/notebooks/nemo/examples/nlp/text_normalization_as_tagging/normalization_as_tagging_infer.py", line 56, in main
_, model = instantiate_model_and_trainer(cfg, ITN_MODEL, False)
File "/nemo_compatible/notebooks/nemo/examples/nlp/text_normalization_as_tagging/helpers.py", line 66, in instantiate_model_and_trainer
raise (
ValueError: ru_g2p_ipa_bert_large/ru_g2p.nemo not in the list of available Tagger models.Select from [PretrainedModelInfo(
pretrained_model_name=itn_en_thutmose_bert,
description=A single-pass tagger-based English model for inverse text normalization basedon BERT, trained on 2 mln sentences from Google Text Normalization Dataset,
location=https://api.ngc.nvidia.com/v2/models/nvidia/nemo/itn_en_thutmose_bert/versions/1.9.0/files/itn_en_thutmose_bert.nemo
), PretrainedModelInfo(
pretrained_model_name=itn_ru_thutmose_bert,
description=A single-pass tagger-based Russian model for inverse text normalization basedon BERT, trained on 2 mln sentences from Google Text Normalization Dataset,
location=https://api.ngc.nvidia.com/v2/models/nvidia/nemo/itn_ru_thutmose_bert/versions/1.11.0/files/itn_ru_thutmose_bert.nemo
)]

Please, can you help? What version of nemo is compatible with your solution?