FluidInference
/

diar-streaming-sortformer-coreml

Automatic Speech Recognition

speech-recognition

Model card Files Files and versions

alexwengg commited on 30 days ago

Commit

fb3bc01

·

verified ·

1 Parent(s): d243db2

Update README.md

Files changed (1) hide show

README.md +2 -5

README.md CHANGED Viewed

@@ -7,7 +7,7 @@
   | Variant | File | Latency | Use Case |
   |---------|------|---------|----------|
-  | **Default** | `Sortformer.mlmodelc` | ~1.12s | Low latency streaming |
   | **NVIDIA Low** | `SortformerNvidiaLow.mlmodelc` | ~1.04s | Low latency streaming |
   | **NVIDIA High** | `SortformerNvidiaHigh.mlmodelc` | ~30.4s | Best quality, offline |
@@ -71,10 +71,7 @@
 ```
   Performance
-  | Metric        | Default | NVIDIA High |
-  |---------------|---------|-------------|
-  | Latency       | ~1.12s  | ~30.4s      |
-  | RTFx (M4 Pro) | ~120x   | ~118x       |
   Files

   | Variant | File | Latency | Use Case |
   |---------|------|---------|----------|
+  | **Default** | `Sortformer.mlmodelc` | ~1.04s | Low latency streaming |
   | **NVIDIA Low** | `SortformerNvidiaLow.mlmodelc` | ~1.04s | Low latency streaming |
   | **NVIDIA High** | `SortformerNvidiaHigh.mlmodelc` | ~30.4s | Best quality, offline |
 ```
   Performance
+https://github.com/FluidInference/FluidAudio/blob/main/Documentation/Benchmarks.md
   Files