Automatic Speech Recognition
MLX
English
apple-silicon
speech-to-text
asr
stt
low-bit
ternary
quantization-aware-training
on-device
streaming
Instructions to use FermionResearch/Phonon-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use FermionResearch/Phonon-1 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Phonon-1 FermionResearch/Phonon-1
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Verify anywhere
Browse files- verify_install.py +0 -3
verify_install.py
CHANGED
|
@@ -6,7 +6,6 @@ from __future__ import annotations
|
|
| 6 |
import argparse
|
| 7 |
import hashlib
|
| 8 |
import json
|
| 9 |
-
import platform
|
| 10 |
import sys
|
| 11 |
from pathlib import Path
|
| 12 |
|
|
@@ -42,8 +41,6 @@ def main() -> int:
|
|
| 42 |
)
|
| 43 |
args = parser.parse_args()
|
| 44 |
model = MODELS[args.profile]
|
| 45 |
-
if platform.machine() != "arm64":
|
| 46 |
-
raise RuntimeError("the optimized local runtime requires Apple Silicon")
|
| 47 |
manifest = json.loads((model / "packed_manifest.json").read_text())
|
| 48 |
if manifest.get("status") != "PASS":
|
| 49 |
raise RuntimeError("packed manifest is not PASS")
|
|
|
|
| 6 |
import argparse
|
| 7 |
import hashlib
|
| 8 |
import json
|
|
|
|
| 9 |
import sys
|
| 10 |
from pathlib import Path
|
| 11 |
|
|
|
|
| 41 |
)
|
| 42 |
args = parser.parse_args()
|
| 43 |
model = MODELS[args.profile]
|
|
|
|
|
|
|
| 44 |
manifest = json.loads((model / "packed_manifest.json").read_text())
|
| 45 |
if manifest.get("status") != "PASS":
|
| 46 |
raise RuntimeError("packed manifest is not PASS")
|