Issues
- 0
fastspeech not support?
#117 opened by soonguKwon - 2
Incorrect handling of export config parameters
#113 opened by espnetUser - 11
Failed to convert Espnet2 model using external (Fbank+Pitch) features to ONNX format
#92 opened by PhenixCFLi - 13
- 1
About TorchDynamo
#110 opened by hexisyztem - 0
About Parameter Settings for Transformation
#109 opened by hexisyztem - 2
About converting to .plan file format
#108 opened by hexisyztem - 1
- 5
Tacotron2 convert onnx issue
#103 opened by shakhbozabdigapporov - 2
Inference error of converted Reazonspeech model
#104 opened by yoquankara - 1
Hardcoded `tag_config_path`
#101 opened by tjysdsg - 1
converting to triton model
#100 opened by Macsim2 - 2
the tts colab notebook does not work anymore
#98 opened by csukuangfj - 14
ONNX Model Fail to run
#95 opened by rajeevbaalwan - 61
- 2
- 1
ModuleNotFoundError: No module named 'espnet_model_zoo.downloader'; 'espnet_model_zoo' is not a package
#93 opened by neso613 - 14
onnxruntime::BroadcastIterator::Append(ptrdiff_t, ptrdiff_t) axis == 1 || axis == largest was false. Attempting to broadcast an axis by a dimension other than 1. 211 by 421
#88 opened by QMZ321 - 16
ASR onnx export accuracy drop
#49 opened by yuekaizhang - 2
testing onnx module encoder
#84 opened by sanjuktasr - 4
Speech2Text.__init__() got an unexpected keyword argument 'train_config' when downloading model
#82 opened by ADD-eNavarro - 1
IndexError: list index out of range
#79 opened by ben-8878 - 2
IndexError: list index out of range
#77 opened by shahizat - 1
Link to custom onnxruntime might be missing
#78 opened by akuzeee - 1
For streaming model result first word is often missing when displaying the best hypo
#74 opened by espnetUser - 7
A difference in accuracy between a onnx conformer model and a torch conformer model.
#38 opened by ken57 - 3
AttributeError: 'ContextualBlockXformerEncoder' object has no attribute 'get_frontend_config'
#57 opened by espnetUser - 3
Quantize model is slower than raw model
#69 opened by jinggaizi - 2
tts onnx gpu inference time problems
#70 opened by 1nlplearner - 1
- 6
Unknown model file format version
#67 opened by ben-8878 - 2
wav quality drop
#68 opened by 1nlplearner - 3
v0.1.9 bug
#32 opened by unparalleled-ysj - 1
Infer rnnt onnx wrong
#58 opened by pengaoao - 2
max_seq_length not working for fastspeech2
#59 opened by sciai-ai - 1
- 1
torch.istft export to onnx format
#64 opened by unparalleled-ysj - 2
The bug caused by torch version
#47 opened by unparalleled-ysj - 2
Can not import "TTSModelExport"
#60 opened by Ht-zhang-xianyu - 2
Dynamic input for TTS
#50 opened by robinhad - 8
- 1
HiFiGAN vocoder support in TTS
#48 opened by ahazned - 1
only support batch_size=1 onnx export? it seems wrong when export muilt batch with different lengths
#45 opened by pengaoao - 3
[Feature request] ESPnet2 standalone Transducer
#44 opened by b-flo - 8
- 1
Conformer-RNN Transducer model export onnx error
#41 opened by pengaoao - 13
xvector-vits conversion error
#37 opened by unparalleled-ysj - 2
(bug)[ONNXRuntimeError] : 2 : INVALID_ARGUMENT
#39 opened by weirdseed - 1
vits inference bug
#34 opened by unparalleled-ysj - 1
about JETS
#31 opened by unparalleled-ysj