open-mmlab/Amphion
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
PythonMIT
Issues
- 14
- 0
[Help]: Loss NaN occured while training VALL-E during the second stage (the NAR decoder)
#211 opened by Ming-er - 0
[Help]: Reproduced TTA Results
#209 opened by KunZhou9646 - 0
- 2
- 4
[Help]: Data preprocessing for NaturalSpeech2 TTS
#179 opened by AvivSham - 1
- 3
[Help]: Question of Data Preparation for TTA
#176 opened by jiusansan222 - 0
natural speech3 FACodec
#207 opened by wwfcnu - 2
[Feature]: Audiocap dataset dev and test files
#186 opened by KunZhou9646 - 1
[Help]: Performance Inferior to Demo Showcase in terms of "FACodec: Voice Conversion Samples"
#203 opened by zyy-fc - 2
- 3
[Help]: Is there any loss that linearly correlate to performance of TTA autoencoder?
#184 opened by Jiang-Stan - 2
[Help]: Questions about FACodec's Parameter
#194 opened by Pydataman - 1
- 1
[Feature]: Use ruff to improve code style
#195 opened by Nugine - 1
- 1
[Help]: Infer AR solely for VALL-E?
#191 opened by caigun - 2
- 1
[Help]: The difference between the FAcodec pretrained model "FACodecEncoderV2" vs "FACodecEncoder"
#192 opened by zyy-fc - 1
- 2
- 9
- 2
[Help]: Some questions about the SVC model
#187 opened by Yuki-zik - 0
[Dataset]: Audiocap dev and test files
#185 opened by KunZhou9646 - 1
[BUG]: missing reference to `modules.generic.conv` in `modules/encoder/conv_encoder.py`
#178 opened by karljeon44 - 1
[Feature]: For Music - VALL-E transformer RAG (and other embedding solutions)
#170 opened by bennmann - 3
[Help]: Latent
#174 opened by a897456 - 2
[Help] How to do data processing of the tta project?
#168 opened by spiralanch - 4
[BUG]: ns2_dataset.py does not have this two part, phones and num_frames, which must be need in ns2_trainer.py
#171 opened by a897456 - 3
[Help]: When using Valle_libritts pre -training model, the model failed to load the model correctly.
#169 opened by song201216 - 1
[Feature]: FACodec training
#156 opened by TechInterMezzo - 2
[Help]: FileNotFoundError: [Errno 2] No such file or directory: 'data\\metadata\\libritts\\train-clean-100#1970#28415#1970_28415_000067_000000.pkl'
#172 opened by a897456 - 6
- 2
[Help]: MultiGPU TTA training
#159 opened by fpicetti - 3
- 4
[Help]: while trainning transfomerSVC
#164 opened by suted2 - 3
- 1
[BUG]: FACodec outputs noise
#173 opened by lifeiteng - 2
[Help]: What configuration of server is appropriate to run this project.
#146 opened by liuyuhualilith - 2
[BUG]: Typos in TTA task
#158 opened by fpicetti - 0
[BUG]: TTA ldm training loss
#162 opened by Sreyan88 - 1
length mismatch for FACodecDecoderV2
#160 opened by chenjiasheng - 1
[BUG]- state_dic saved by "accelerator" cannot be load due to "shared tensors" problem
#149 opened by zyy-fc - 1
[Help]: May I ask when naturalspeech3_facodec/resolve/main/ns3_facodec_encoder_v2.bin will be released?
#157 opened by wcr369 - 2
[Help]: Need a list of hardware configurations.
#151 opened by isKEKE - 0
- 2
[BUG]-NaturalSpeech2 data preprocess & pitch loss
#148 opened by zyy-fc - 5
[Help]: Inference
#142 opened by mysxs - 0