BlueTTSV2 - Multilingual text-to-speech With VC
🔊
6
Generate spoken audio from text in multiple languages
Doron Adler PRO
Norod78
AI & ML interests
Fooling around with Generative machine learning models.
Recent Activity
liked a Space 33 minutes ago
notmax123/BlueV2 liked a Space 38 minutes ago
Alissonerdx/ltx-best-face-id liked a dataset 42 minutes ago
davanstrien/search-v3-embeddingsOrganizations
liked a
Space 33 minutes ago
liked a
Space 38 minutes ago
liked a
dataset 42 minutes ago
liked a
model about 2 hours ago
liked a
dataset 3 days ago
upvoted an article 9 days ago
Article
Security incident disclosure — July 2026
system
• • 661 upvoted a changelog 10 days ago
Hugging Face Changelog
Build Spaces with AI Agents
• 123
liked a
Space 11 days ago
liked 2
Spaces 21 days ago
updated 2
Spaces 24 days ago
updated a
Space 26 days ago
liked a
model 26 days ago
reacted to eabdullin's post with 🔥🤗 about 2 months ago
Post
5736
I’m doing a PhD in AI, which sounds impressive until you realize it mostly means I spend three years trying to make a computer say something slightly less stupid than it said yesterday.
People hear "AI researcher" and they think I’m building the future. No. I’m in a basement at 2 a.m. Googling, "CUDA error what the f**k does this mean."
And the worst part about AI research now is compute. You don’t even ask, "Is this idea good?" anymore. You ask, "Can I afford for this idea to be wrong?"
My advisor comes to me one day and says, "I think we should fine-tune our own language model."
I said, "Professor, with what money? I’m a PhD student. I have two bank accounts: checking and emotionally checking."
He goes, "Don’t worry. We have compute."
Now, in academia, "don’t worry" is never the beginning of a good sentence.
I said, "What do you mean we have compute?"
He said, "My friend knows the cluster admin. He can get us on the GPUs."
I said, "Okay… what do we have to do?"
He goes, "Nothing crazy. Just be very grateful in the acknowledgements."
I said, "How grateful?"
He said, "Maybe put him as co-author."
I said, "Co-author? Are we using the cluster, or is the cluster using us?"
Because at that point, that’s not a favor. That’s academic child support.
So I go to the server room, and the cluster admin walks up to me and goes, "So you’re the NLP student."
And in my head I’m like, "No, tonight you’re the principal investigator. You’re the provider. I’m just a little token waiting to be attended to."
Because whoever controls the GPUs controls the relationship. That’s lab romance.
He starts setting things up, and I’m trying to act casual, but I don’t understand any of the numbers he’s saying.
He’s like, "Yeah, I can probably give you four H100s for the weekend."
I’m nodding like, "Mmm. Four. Weekend. H. One hundred. Absolutely."
Inside I’m like, "Is that good? Is that prison time? Why did he say it like he was offering me organs?"
[Continue in comments...]
People hear "AI researcher" and they think I’m building the future. No. I’m in a basement at 2 a.m. Googling, "CUDA error what the f**k does this mean."
And the worst part about AI research now is compute. You don’t even ask, "Is this idea good?" anymore. You ask, "Can I afford for this idea to be wrong?"
My advisor comes to me one day and says, "I think we should fine-tune our own language model."
I said, "Professor, with what money? I’m a PhD student. I have two bank accounts: checking and emotionally checking."
He goes, "Don’t worry. We have compute."
Now, in academia, "don’t worry" is never the beginning of a good sentence.
I said, "What do you mean we have compute?"
He said, "My friend knows the cluster admin. He can get us on the GPUs."
I said, "Okay… what do we have to do?"
He goes, "Nothing crazy. Just be very grateful in the acknowledgements."
I said, "How grateful?"
He said, "Maybe put him as co-author."
I said, "Co-author? Are we using the cluster, or is the cluster using us?"
Because at that point, that’s not a favor. That’s academic child support.
So I go to the server room, and the cluster admin walks up to me and goes, "So you’re the NLP student."
And in my head I’m like, "No, tonight you’re the principal investigator. You’re the provider. I’m just a little token waiting to be attended to."
Because whoever controls the GPUs controls the relationship. That’s lab romance.
He starts setting things up, and I’m trying to act casual, but I don’t understand any of the numbers he’s saying.
He’s like, "Yeah, I can probably give you four H100s for the weekend."
I’m nodding like, "Mmm. Four. Weekend. H. One hundred. Absolutely."
Inside I’m like, "Is that good? Is that prison time? Why did he say it like he was offering me organs?"
[Continue in comments...]
- 1 reply
reacted to matteospanio's post with 🚀 about 2 months ago
Post
7090
🎶 Released mule-torch — an unofficial PyTorch port of MULE (SF-NFNet-F0), SiriusXM/Pandora's music-audio embedding model (McCallum et al., ISMIR 2022).
No retraining: I re-implemented the architecture in pure PyTorch and transferred the original TensorFlow weights, then checked it layer by layer against the genuine TF pipeline.
✅ End-to-end clip-embedding cosine 0.9999999 vs the original
✅ ONNX backbone parity < 1e-6
✅ 62.35M params (paper: ~62.4M)
✅ Batched, GPU-native, ONNX-exportable — none of which the original
🤗 Weights: matteospanio/mule
💻 Code: https://github.com/matteospanio/mule-torch
📦 PyPI: https://pypi.org/project/mule-torch/
The fun bug: parity was perfect through every conv but the block output was anti-correlated (cos = −1). Cause: the learnable skip-init gains couldn't be mapped by layer name (Keras scrambles the order) — they had to be recovered from the graph.
⚠️ Unofficial, community port — not affiliated with or endorsed by the original authors. All credit to them; please cite the paper. Weights inherit CC-BY-NC-4.0.
No retraining: I re-implemented the architecture in pure PyTorch and transferred the original TensorFlow weights, then checked it layer by layer against the genuine TF pipeline.
✅ End-to-end clip-embedding cosine 0.9999999 vs the original
✅ ONNX backbone parity < 1e-6
✅ 62.35M params (paper: ~62.4M)
✅ Batched, GPU-native, ONNX-exportable — none of which the original
Analysis pipeline doespip install mule-torchfrom mule_torch import MuleModel
emb = MuleModel.from_pretrained()(waveform) # (B, T)@16kHz -> (B, 1728)🤗 Weights: matteospanio/mule
💻 Code: https://github.com/matteospanio/mule-torch
📦 PyPI: https://pypi.org/project/mule-torch/
The fun bug: parity was perfect through every conv but the block output was anti-correlated (cos = −1). Cause: the learnable skip-init gains couldn't be mapped by layer name (Keras scrambles the order) — they had to be recovered from the graph.
⚠️ Unofficial, community port — not affiliated with or endorsed by the original authors. All credit to them; please cite the paper. Weights inherit CC-BY-NC-4.0.
liked 3
Spaces about 2 months ago