Downloads · 30 days
0
visualears-fastconformer-fa-depoisoned-phaseB-streaming-mlx-fp16
Reza2kn/visualears-fastconformer-fa-depoisoned-phaseB-streaming-mlx-fp16
visualears-fastconformer-fa-depoisoned-phaseB-streaming-mlx-fp16 is a automatic speech recognition model from Reza2kn. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as cc-by-nc-4.0.
MLX FP16 weight bundle and RNNT runtime scaffold for Reza2kn/visualears-fastconformer-fa-depoisoned-phaseB.
Access
Public
Updated Jun 20, 2026
Repo size
229 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors229 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Jun 20, 2026
- Updated
- Jun 20, 2026
- SHA
- 067728d7
Base models
Model card
From the Hugging Face model README
VisualEars PhaseB Streaming MLX FP16
MLX FP16 weight bundle and RNNT runtime scaffold for Reza2kn/visualears-fastconformer-fa-depoisoned-phaseB.
Files:
phaseB_hybrid_streaming_fp16.safetensorsphaseB_hybrid_streaming_fp16_mlx_manifest.jsonphaseb_mlx_rnnt_runtime.pymlx_rnnt_runtime_smoke.jsonmlx_vs_torch_rnnt_argmax20.json
Validation: MLX RNNT predictor/joint smoke passed; RNNT joint argmax matched TorchScript on 20 random probes.
The MLX encoder port is not complete in this artifact set. The exported weights and manifest preserve the streaming cache/head metadata for the full hybrid model.
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- cc-by-nc-4.0
- Languages
- fa
- Created
- Jun 20, 2026
- Updated
- Jun 20, 2026