Akhil Tolani

@Zlikster currently taking 2 weeks to get to epoch 256 on a small 437M param with 200k files with 4xA100 80Gb

@sanchit-gandhi / @adamfils Thank you for providing a detailed response! I have a large dataset of around 1k hours of just vocals (_separated out of music from soundcloud songs using...

Same issue here. I believe you have to use `fsdp = true` & `autocast = false`.

@ylacombe I curated the dataset of 1000 hours of vocals (_mostly english_) Would love to hear your thoughts whether this dataset could work - • audio + transcriptions - https://huggingface.co/datasets/AkhilTolani/vocals...

> Hey @Saltb0xApps, wow thanks for sharing this! How did you create this dataset out of curiosity? > > A few remarks: > > * I'm pretty sure the model...

> Thank you also for sharing your logs, they bring a lot of value to the community! I really like your initiative! If you're okay with this, we can probably...

> I've listened to some samples, the model seems to get a sense of singing, which is a good sign! It'd probably need some better hyper-parameters though! > > Re:...

@ylacombe I believe parler-tts is going to come up with a larger model very soon if i remember correctly? 600M is comparable to musicgen-small, and i believe there is a...

Here is a Huggingface space to try out the singing vocals fine-tune of Parler-tts! https://huggingface.co/spaces/AkhilTolani/vocals 1. The model is having a very hard time differentiating between male and female vocals....

I believe the issue i'm facing here is due to the changes that were recently made to the Tatum contracts for marketplace - 1. https://github.com/tatumio/smart-contracts/commit/b49fcbe33063ed06342694264b5fe921b1510205 2. https://github.com/tatumio/smart-contracts/commit/8a8ed56cd5425b64710d14cdc32ca762c456bbb6 The timing when...