Automatic Speech Recognition
MLX
English
parakeet_tdt_five_value
apple-silicon
speech-to-text
asr
stt
on-device
Eval Results
Instructions to use FermionResearch/Phonon-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use FermionResearch/Phonon-2 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download FermionResearch/Phonon-2 --local-dir Phonon-2
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Run it: word timestamps and the documentation link
Browse files
README.md
CHANGED
|
@@ -58,6 +58,8 @@ phonon transcribe recording.wav
|
|
| 58 |
fermion transcribe phonon-2 recording.wav
|
| 59 |
```
|
| 60 |
|
|
|
|
|
|
|
| 61 |
The same package runs on Linux (x86-64 and Arm) and Windows CPUs; the engines are at [github.com/fermionresearch/phonon](https://github.com/fermionresearch/phonon). With Docker,
|
| 62 |
on a CPU or a GPU:
|
| 63 |
|
|
|
|
| 58 |
fermion transcribe phonon-2 recording.wav
|
| 59 |
```
|
| 60 |
|
| 61 |
+
`--json` adds a start and end time for every word. The command line and the server are documented at [fermionresearch.com/docs/speech](https://www.fermionresearch.com/docs/speech/).
|
| 62 |
+
|
| 63 |
The same package runs on Linux (x86-64 and Arm) and Windows CPUs; the engines are at [github.com/fermionresearch/phonon](https://github.com/fermionresearch/phonon). With Docker,
|
| 64 |
on a CPU or a GPU:
|
| 65 |
|