Request for Access to SAM-Audio Checkpoint for Research and Learning
I hope this message finds you well. My name is CanyueMa, and I am a student currently engaged in speech enhancement. I recently requested access to the gated checkpoint for the SAM-Audio model on Hugging Face but unfortunately received a rejection. I am writing to kindly request that you reconsider granting access.
I would like to provide more context about my intended use:
Affiliation: Inner Mongolia University
Intended Use: My primary purpose for accessing the SAM-Audio checkpoint is for scientific research and educational learning only. I plan to use the model for inference on custom audio data to evaluate its separation capabilities and to better understand its performance characteristics in comparison with other models. Based on the results, I may explore integrating the model into future research projects focusing on audio source separation and related multimodal tasks.
Non-Commercial Nature: This work is strictly non-commercial and will be used solely for academic and learning purposes.
Since the public repository does not include full training code or publicly accessible weights, access to the official checkpoint is essential for me to meaningfully work with SAM-Audio and validate its performance in my research pipelines. Without the checkpoint, I cannot fully execute the inference examples or benchmark the model.
I fully understand that this model is gated and agree to comply with any usage guidelines or restrictions you deem appropriate. I would be grateful if you could review my request again and grant access to the checkpoint. I am also happy to provide any additional information about my research background or use case if needed.
Thank you very much for your time and consideration. I look forward to your response.
Sincerely,
CanyueMa