Instructions to use starkdmi/MossFormer2_SR_48K_MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use starkdmi/MossFormer2_SR_48K_MLX with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MossFormer2_SR_48K_MLX starkdmi/MossFormer2_SR_48K_MLX
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
MossFormer2 SR 48K (MLX)
Audio super resolution, 16 kHz in to 48 kHz out. This model was converted to MLX format from alibabasglab/MossFormer2_SR_48K.
Code: starkdmi/mossformer_sr_mlx
Files
| file | size |
|---|---|
model_fp32.safetensors |
418 MiB |
model_int8.safetensors |
293 MiB |
config.json |
392 B |
config.json is required: this model builds its architecture from the file rather
than hardcoding one, so a download without it cannot load.
Precision
| precision | size | speed | peak memory | quality vs fp32 |
|---|---|---|---|---|
| fp32 | 418 MiB | 2.1x | 4149 MiB | reference |
| int8 | 293 MiB | 2.1x | 3985 MiB | 62.5 dB |
Bold marks the best value in each column. Quality is int8 against this model's own fp32 output โ the cost of the precision change, not a score for the model.
Integer quantization reaches only the Linear modules, and this model's Generator
is almost entirely convolutions, so speed and memory are close to unchanged
between the two. int8 trades 30% of the download for 62.5 dB.
Measured on an Apple M1 Pro (16 GB), 30 s of audio, three timed runs per configuration; speed is realtime factor. These are single-machine figures โ expect different absolute numbers on other hardware, and treat the ordering as indicative rather than guaranteed.
Used by
- Downloads last month
- 52
Quantized
Model tree for starkdmi/MossFormer2_SR_48K_MLX
Base model
alibabasglab/MossFormer2_SR_48K