Awni Hannun
ec14583c2a
work with tuple shape ( #393 )
2024-02-01 13:03:47 -08:00
Yousif
7575125d5d
Added lora support for Phi-2 ( #302 )
...
* Added lora support for Phi-2
* Added Phi-2 support in fuse and convert
* format + readme
---------
Co-authored-by: Awni Hannun <awni@apple.com>
2024-01-12 13:45:30 -08:00
Alexandre Boucaud
3ac731dd4f
Fix TypeError in whisper benchmark script ( #306 )
...
* Add missing keyword to the decoding options
* Reverting last commit
* Fixing transcribe keyword in benckmark.py
* Add argument name to load_model
This is intended to avoid confusion
2024-01-12 13:07:15 -08:00
Awni Hannun
c1342b8e89
Use pip for mlx data with speech commands ( #307 )
...
* update to use pypi mlx data
* nit in readme
2024-01-12 11:06:33 -08:00
Awni Hannun
80d18671ad
[Lora] Fix generate ( #282 )
...
* fix generate
* update readme, fix test, better default
* nits
* typo
2024-01-10 16:13:06 -08:00
Vaibhav Srivastav
bb35e878cb
[Whisper] Add load from Hub. ( #255 )
...
* Add load from Hub.
* Up.
2024-01-08 06:20:00 -08:00
Vaibhav Srivastav
d4c3a9cb54
[Whisper] Add HF Hub upload option. ( #254 )
...
* Add HF Hub upload option.
* up.
* Add missing requirements.
2024-01-08 06:18:24 -08:00
bofeng huang
bf9926489e
[Whisper] Add word timestamps and confidence scores ( #201 )
...
* Add word timestamps and confidence scores
* Create a separate forward_with_cross_qk function
* Move multiple ops from np to mlx, clean comments
* Save alignment_heads
* Cast qk to fp32
* Add test for word-level timestamps and confidence scores
* format + readme
* nit
---------
Co-authored-by: Awni Hannun <awni@apple.com>
2024-01-07 10:01:29 -08:00
Awni Hannun
a5d6d0436c
Support Hugging Face models ( #215 )
...
* support hf direct models
2024-01-03 15:13:26 -08:00
bofeng huang
581a5733a1
[Whisper] Load customized MLX model & Quantization ( #191 )
...
* Add option to load customized mlx model
* Add quantization
* Apply reviews
* Separate model conversion and loading
* Update test
* Fix benchmark
* Add notes about conversion
* Improve doc
2023-12-29 10:22:15 -08:00
Dimo
07c163d9d9
[Whisper] Large-v3 requires 128 Mel frequency bins ( #193 )
...
* Large-v3 requires 128 Mel frequency bins
* extract correct model dimensions and use argparse
* format
* format
---------
Co-authored-by: Awni Hannun <awni@apple.com>
2023-12-28 13:50:35 -08:00
bofeng huang
e1e56a625b
Fix benchmark ( #200 )
2023-12-28 11:29:39 -08:00
Awni Hannun
27c0a8c002
Add llms subdir + update README ( #145 )
...
* add llms subdir + update README
* nits
* use same pre-commit as mlx
* update readmes a bit
* format
2023-12-20 10:22:25 -08:00
Awni Hannun
b863e7cca0
format
2023-12-14 16:56:50 -08:00
Stv.X
cbae83e011
Corrected spelling of terms in whisper/README.md
2023-12-14 08:15:26 +08:00
bofenghuang
4b1a06c0cb
Fix fp16
2023-12-13 11:07:47 +01:00
Awni Hannun
74c4ed40d2
Merge pull request #76 from bofenghuang/add-whisper-large-v3
...
Add whisper-large-v3
2023-12-12 20:22:31 -08:00
bofenghuang
94705ed38b
Add large v3
2023-12-12 17:26:52 +01:00
Awni Hannun
6e723a015a
whisper default in fp16
2023-12-12 07:37:35 -08:00
Awni Hannun
172a60056f
update whisper readme and requirements
2023-12-07 13:01:44 -08:00
Awni Hannun
54952a0d80
Merge pull request #12 from chatgpt-1/main
...
Fix: timestamp extraction bug in transcribe function
2023-12-07 08:53:30 -08:00
adhishthite
9cf82a0d43
Benchmark all models if user allows.
2023-12-07 00:07:42 +05:30
crackerben
6cbc029450
Fix timestamp extraction bug in transcribe function
2023-12-06 20:34:30 +08:00
Awni Hannun
31bc57c4ff
add copyright in source
2023-11-30 11:08:53 -08:00
Awni Hannun
b243c1d8f4
a few examples
2023-11-29 08:17:26 -08:00
