Potsawee Manakul PRO

potsawee's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a Space 2 days ago

Running on Zero

2

TextSyncMimi Speech Editing

🎙

2

Swap speech embeddings at token positions to edit audio

liked a Space 5 days ago

Running on CPU Upgrade

Featured

87

Cohere Multilingual ASR

🎙

87

Transcribe audio clips to text in many languages

upvoted a paper 6 days ago

Problems with Chinchilla Approach 2: Systematic Biases in IsoFLOP Parabola Fits

Paper • 2603.22339 • Published 14 days ago • 5

published a dataset 19 days ago

potsawee/video-batch-20260316

Updated 19 days ago • 605

updated a dataset 19 days ago

potsawee/video-batch-20260316

Updated 19 days ago • 605

upvoted a collection 19 days ago

Typhoon ASR

Collection

A speech to text model for Thai • 9 items • Updated Jan 28 • 3

published a dataset 22 days ago

potsawee/audio-mia-batch-20260312

Viewer • Updated 22 days ago • 7k • 105

updated a dataset 23 days ago

potsawee/audio-mia-batch-20260312

Viewer • Updated 22 days ago • 7k • 105

updated a Space 24 days ago

Running on Zero

2

TextSyncMimi Speech Editing

🎙

2

Swap speech embeddings at token positions to edit audio

updated a collection about 1 month ago

MQAG Models

Collection

Models developed in the MQAG paper -- https://arxiv.org/abs/2301.12307 • 5 items • Updated Feb 27

liked 3 models about 1 month ago

typhoon-ai/typhoon-s-thaillm-8b-instruct-research-preview

Text Generation • 8B • Updated Mar 2 • 1.87k • 3

marin-community/marin-32b-base

Text Generation • 33B • Updated Nov 3, 2025 • 261 • 47

marin-community/marin-8b-instruct

Text Generation • 8B • Updated May 19, 2025 • 1.6k • • 27

New activity in potsawee/soda-demo about 1 month ago

Thanks a Million for This HF Space!

1

#1 opened about 1 month ago by

9voltfan2009

upvoted a paper about 1 month ago

Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens

Paper • 2602.16687 • Published Feb 18 • 5

authored a paper about 1 month ago

Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens

Paper • 2602.16687 • Published Feb 18 • 5