Update README.md
Browse files
README.md
CHANGED
|
@@ -18,23 +18,15 @@ This is a quantized NVFP4 (W4A4) version of Step-Audio-R1, an open-weights Audio
|
|
| 18 |
The original BF16 model requires ~67 GB VRAM.
|
| 19 |
|
| 20 |
Step-Audio-R1 combines:
|
| 21 |
-
|
| 22 |
A high-capacity audio encoder
|
| 23 |
-
|
| 24 |
A projection layer that maps audio features into the transformer
|
| 25 |
-
|
| 26 |
A language backbone for reasoning and text generation
|
| 27 |
|
| 28 |
The model is designed for:
|
| 29 |
-
|
| 30 |
Speech transcription and interpretation
|
| 31 |
-
|
| 32 |
Emotional / tonal analysis
|
| 33 |
-
|
| 34 |
Speaker characteristics
|
| 35 |
-
|
| 36 |
Music and sound-scene understanding
|
| 37 |
-
|
| 38 |
High-quality step-by-step reasoning about audio inputs
|
| 39 |
|
| 40 |
It does not generate audio; it produces text based on audio input.
|
|
|
|
| 18 |
The original BF16 model requires ~67 GB VRAM.
|
| 19 |
|
| 20 |
Step-Audio-R1 combines:
|
|
|
|
| 21 |
A high-capacity audio encoder
|
|
|
|
| 22 |
A projection layer that maps audio features into the transformer
|
|
|
|
| 23 |
A language backbone for reasoning and text generation
|
| 24 |
|
| 25 |
The model is designed for:
|
|
|
|
| 26 |
Speech transcription and interpretation
|
|
|
|
| 27 |
Emotional / tonal analysis
|
|
|
|
| 28 |
Speaker characteristics
|
|
|
|
| 29 |
Music and sound-scene understanding
|
|
|
|
| 30 |
High-quality step-by-step reasoning about audio inputs
|
| 31 |
|
| 32 |
It does not generate audio; it produces text based on audio input.
|