Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / NVIDIA/flowtron issues and pull requests

#44 - Higher number of frames inference issue

Issue - State: closed - Opened by artemg over 4 years ago - 4 comments

#44 - Higher number of frames inference issue

Issue - State: closed - Opened by artemg over 4 years ago - 4 comments

#43 - Bad attention weights

Issue - State: open - Opened by dmitrii-obukhov over 4 years ago - 23 comments

#43 - Bad attention weights

Issue - State: open - Opened by dmitrii-obukhov over 4 years ago - 23 comments

#42 - nan loss

Issue - State: closed - Opened by kurbobo over 4 years ago - 2 comments

#42 - nan loss

Issue - State: closed - Opened by kurbobo over 4 years ago - 2 comments

#41 - Model training too long without alignment.

Issue - State: open - Opened by brandokoch over 4 years ago - 4 comments

#41 - Model training too long without alignment.

Issue - State: open - Opened by brandokoch over 4 years ago - 4 comments

#40 - NaN While Training

Issue - State: closed - Opened by lachjames over 4 years ago - 2 comments

#39 - Training issue with Male voice

Issue - State: open - Opened by akshay4malik over 4 years ago - 47 comments

#38 - can we use an alternative vocoder?

Issue - State: open - Opened by ttambe over 4 years ago - 1 comment

#38 - can we use an alternative vocoder?

Issue - State: open - Opened by ttambe over 4 years ago - 1 comment

#37 - KeyError: "state_dict" for every waveglow model I've tried

Issue - State: closed - Opened by lachjames over 4 years ago - 4 comments

#36 - Synthesis by batches

Issue - State: closed - Opened by Yannecc over 4 years ago - 3 comments

#36 - Synthesis by batches

Issue - State: closed - Opened by Yannecc over 4 years ago - 3 comments

#35 - Cannot change speaker for interpolation

Issue - State: open - Opened by DamienToomey over 4 years ago - 5 comments

#35 - Cannot change speaker for interpolation

Issue - State: open - Opened by DamienToomey over 4 years ago - 5 comments

#34 - Accent transfer?

Issue - State: closed - Opened by machineko over 4 years ago - 4 comments

#34 - Accent transfer?

Issue - State: closed - Opened by machineko over 4 years ago - 4 comments

#33 - How is interpolation between speakers performed?

Issue - State: closed - Opened by youmebangbang over 4 years ago - 2 comments

#32 - Can't attend in the second flow (non-english dataset)

Issue - State: closed - Opened by blx0102 over 4 years ago - 25 comments

#31 - training issues

Issue - State: closed - Opened by zjFFFFFF over 4 years ago - 6 comments

#31 - training issues

Issue - State: closed - Opened by zjFFFFFF over 4 years ago - 6 comments

#30 - What are the attention_weights_1 and attention_weights_2 ?

Issue - State: closed - Opened by youmebangbang over 4 years ago - 4 comments

#30 - What are the attention_weights_1 and attention_weights_2 ?

Issue - State: closed - Opened by youmebangbang over 4 years ago - 4 comments

#29 - Deploying model after training

Issue - State: closed - Opened by yiss over 4 years ago - 6 comments

#29 - Deploying model after training

Issue - State: closed - Opened by yiss over 4 years ago - 6 comments

#28 - Pass text embedding dim as a parameter to Encoder

Pull Request - State: closed - Opened by gloriouskilka over 4 years ago - 1 comment

#28 - Pass text embedding dim as a parameter to Encoder

Pull Request - State: closed - Opened by gloriouskilka over 4 years ago - 1 comment

#27 - byte mask fix

Pull Request - State: open - Opened by karkirowle over 4 years ago

#27 - byte mask fix

Pull Request - State: open - Opened by karkirowle over 4 years ago

#26 - Style transfer COLAB

Issue - State: open - Opened by karkirowle over 4 years ago - 10 comments

#26 - Style transfer COLAB

Issue - State: open - Opened by karkirowle over 4 years ago - 10 comments

#25 - Can n_frames_per_step only be 1?

Issue - State: closed - Opened by zzw922cn over 4 years ago - 3 comments

#25 - Can n_frames_per_step only be 1?

Issue - State: closed - Opened by zzw922cn over 4 years ago - 3 comments

#24 - Changing speed of speech

Issue - State: open - Opened by sgulasekaran over 4 years ago - 6 comments

#24 - Changing speed of speech

Issue - State: open - Opened by sgulasekaran over 4 years ago - 6 comments

#23 - KeyError: 'iteration' when training using a pre-trained model

Issue - State: closed - Opened by ghwn over 4 years ago - 3 comments

#22 - How can I implement style transfer with inference.py ?

Issue - State: closed - Opened by xiaoyangnihao over 4 years ago - 1 comment

#21 - why autoregressive doesn't need revertible?

Issue - State: closed - Opened by xusongvae over 4 years ago - 3 comments

#20 - Attention is flat line

Issue - State: closed - Opened by BlazJurisic over 4 years ago - 26 comments

#20 - Attention is flat line

Issue - State: closed - Opened by BlazJurisic over 4 years ago - 26 comments

#19 - Unintelligible speech - inference on pre-trained models

Issue - State: closed - Opened by adrianastan over 4 years ago - 4 comments

#18 - Saving state_dict in the checkpoint?

Issue - State: closed - Opened by adrianastan over 4 years ago - 2 comments

#17 - How can I reproduce the performance of flowtron_ljs.pt?

Issue - State: closed - Opened by jaeseongyou over 4 years ago - 1 comment

#16 - fix inference model loading process

Pull Request - State: open - Opened by daun-io over 4 years ago

#16 - fix inference model loading process

Pull Request - State: open - Opened by daun-io over 4 years ago

#15 - update readme to help users who is migrating data

Pull Request - State: open - Opened by daun-io over 4 years ago

#15 - update readme to help users who is migrating data

Pull Request - State: open - Opened by daun-io over 4 years ago

#14 - fix inference model loading process

Pull Request - State: closed - Opened by daun-io over 4 years ago

#14 - fix inference model loading process

Pull Request - State: closed - Opened by daun-io over 4 years ago

#13 - Create inference_colab.ipynb

Pull Request - State: open - Opened by yhgon over 4 years ago - 2 comments

#13 - Create inference_colab.ipynb

Pull Request - State: open - Opened by yhgon over 4 years ago - 2 comments

#12 - training issues

Issue - State: closed - Opened by asmodaay over 4 years ago - 28 comments

#12 - training issues

Issue - State: closed - Opened by asmodaay over 4 years ago - 28 comments

#11 - Repetitive generation with punctuation

Issue - State: closed - Opened by dakshvar22 over 4 years ago - 4 comments

#10 - updated requirements.txt

Pull Request - State: open - Opened by erekgit over 4 years ago - 5 comments

#9 - Style transfer

Issue - State: open - Opened by karkirowle over 4 years ago - 11 comments

#8 - How does one cut one up a longer text so it fits into the available frames?

Issue - State: open - Opened by Quasimondo over 4 years ago - 6 comments

#7 - Speaker id argument

Issue - State: open - Opened by ilnmtlbnm over 4 years ago - 8 comments

#6 - Write inference output to specified output directory

Pull Request - State: closed - Opened by wietsedv over 4 years ago - 1 comment

#5 - WaveGlow v4 model

Issue - State: closed - Opened by wietsedv over 4 years ago - 3 comments

#4 - Update requirements.txt

Pull Request - State: closed - Opened by artemg over 4 years ago - 1 comment

#3 - how to obtain models/waveglow_256channels_v4.pt for the Inference demo?

Issue - State: closed - Opened by erekgit over 4 years ago - 7 comments

#2 - Docker support

Issue - State: open - Opened by miolini over 4 years ago - 4 comments

#1 - Harcoded paths in the code

Issue - State: closed - Opened by artemg over 4 years ago - 5 comments