Any-to-Any
Transformers
Safetensors
multilingual
spev
feature-extraction
multimodal
text
audio
image
video
decision-model
choice
qwen3-omni
lora
custom-code
custom_code
Instructions to use SpragAI/SPEV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SpragAI/SPEV with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SpragAI/SPEV", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add production audio and image latency results
Browse files- MANIFEST.json +2 -2
- README.md +11 -0
MANIFEST.json
CHANGED
|
@@ -12,8 +12,8 @@
|
|
| 12 |
},
|
| 13 |
{
|
| 14 |
"path": "README.md",
|
| 15 |
-
"bytes":
|
| 16 |
-
"sha256": "
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"path": "THIRD_PARTY_NOTICES.md",
|
|
|
|
| 12 |
},
|
| 13 |
{
|
| 14 |
"path": "README.md",
|
| 15 |
+
"bytes": 4119,
|
| 16 |
+
"sha256": "73d6815884bd212924e2cd7450f42897ac67bc4feeb9883eaa9d8d39bb287993"
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"path": "THIRD_PARTY_NOTICES.md",
|
README.md
CHANGED
|
@@ -105,6 +105,17 @@ do not supply a sample-rate argument. Supply a video's soundtrack separately as
|
|
| 105 |
| `requirements.txt` | Inference dependencies |
|
| 106 |
| `LICENSE` | Apache-2.0 license |
|
| 107 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
## License
|
| 109 |
|
| 110 |
Apache-2.0. See [LICENSE](LICENSE) and [third-party notices](THIRD_PARTY_NOTICES.md).
|
|
|
|
| 105 |
| `requirements.txt` | Inference dependencies |
|
| 106 |
| `LICENSE` | Apache-2.0 license |
|
| 107 |
|
| 108 |
+
## Latency
|
| 109 |
+
|
| 110 |
+
| Input | SPEV p50 / p95 | OpenAI p50 / p95 |
|
| 111 |
+
|---|---:|---:|
|
| 112 |
+
| 5-second audio | 166 / 191 ms | 752 / 1331 ms |
|
| 113 |
+
| 20-second audio | 216 / 270 ms | 997 / 1326 ms |
|
| 114 |
+
| 512 × 512 image | 183 / 283 ms | 194 / 334 ms |
|
| 115 |
+
| 1024 × 1024 image | 322 / 642 ms | 373 / 763 ms |
|
| 116 |
+
|
| 117 |
+
Warm public-HTTPS latency including RTT, measured from the same client with concurrency one. SPEV ran on an RTX PRO6000 with native vLLM pooling. Each row has 30 measured pairs over six fixtures after three warmup pairs. OpenAI used `gpt-6-luna`; audio includes a fresh `gpt-4o-mini-transcribe` request before Decisions. These measurements cover latency, not accuracy.
|
| 118 |
+
|
| 119 |
## License
|
| 120 |
|
| 121 |
Apache-2.0. See [LICENSE](LICENSE) and [third-party notices](THIRD_PARTY_NOTICES.md).
|