62b51c3070
models : change convert-pt-to-ggml to use .tiktoken tokenizer files ( #725 )
2023-04-14 19:50:39 +03:00
18e6fb0287
models : handle spaces and special characters in shell script paths ( #677 )
...
This commit modifies the `get_script_path` function to correctly handle
spaces and special characters in directory paths. The fix involves adding
double quotes around variables and commands where needed to ensure proper
parsing of paths with spaces and special characters.
2023-03-29 23:38:33 +03:00
992aa2cd1b
models : change default encoding to utf8 ( #605 )
2023-03-22 21:17:24 +02:00
1beff6f66d
models : change HF hosting from dataset to model
2023-03-22 20:44:56 +02:00
d629c034a4
models : fix HF model URL ( close #356 )
2023-01-02 09:54:43 +02:00
3467230a77
models : fix typo in convert-h5-to-ggml.py
...
signficant -> significant
2022-12-31 09:49:01 +02:00
77226aa89d
models : fix support for spaces in path ( close #315 )
2022-12-23 11:11:38 +02:00
a613f16aec
talk : improve prompting
2022-12-12 23:44:36 +02:00
d91c001120
Fix paths echoed after the download
...
Was using models path instead of root path
2022-12-08 09:23:52 +02:00
9fe7306f4b
models : add the new "large" model release by OpenAI
...
The old "large" model is now renamed "large-v1".
If you have been using it, make sure to rename it and download the new
"large" model for best results.
2022-12-06 18:48:57 +02:00
abce28ea99
talk.wasm : move to https://whisper.ggerganov.com/talk
...
This way, we can share the same models across different WASM examples
and not have to download them for each page
2022-11-24 18:24:06 +02:00
a2ecd54455
models : add instructions for using HF fine-tuned models
2022-11-24 17:54:41 +02:00
00f46dbc1d
models : add usage comments to the HF convert script ( #157 )
2022-11-23 23:22:40 +02:00
5698bddbc9
models : fix HF fine-tuned model conversion script ( #157 )
...
It works now
2022-11-23 23:14:11 +02:00
d64d6ca3fd
models : minor changes to the HF convert script ( #157 )
2022-11-23 22:07:20 +02:00
93482d0373
models : add "convert-h5-to-ggml.py" script ( #157 )
...
Converts transformers models to ggml.
Although the conversion is successful, it does not work for some reason.
Not sure why
2022-11-23 17:19:22 +02:00
e70e5c8b53
models : simplify the conversion script
...
"transformers" dependency is not actually needed
2022-11-16 19:22:32 +02:00
55a0e1a64e
Update download-ggml-model.sh
...
follow curl redirect to new hosting site
2022-11-16 18:59:44 +02:00
864a78a8d0
models : change default hosting to Hugging Face
...
My Linode is running out of monthly bandwidth due to the big interest in
the project
2022-11-15 19:47:06 +02:00
46a68fb9b5
minor : remove one more redundant line
2022-11-11 18:02:58 +02:00
ccd56a9c5b
minor : fix double float32 conversion in python script
2022-11-11 17:58:51 +02:00
b5dde365e9
extra : compute SHA of all models files
2022-11-02 18:31:55 +02:00
b26345cc7b
Added for Windows implemenated script download-ggml-model.cmd
2022-10-31 19:38:20 +02:00
a09ce6e889
Changes to work by default on macOS - use curl when wget is not available, and use an alternative method to get the script path when realpath is not available.
2022-10-26 12:18:18 +03:00
c6710efde2
refactoring : move main + stream in examples + other stuff
2022-10-25 20:53:48 +03:00
4e887dc350
Add enconding parameter to vocab.json opening to fix errors
2022-10-23 11:55:01 +03:00
6b45e37b2b
Update README.md and finalize the whisper.wasm example
2022-10-22 18:54:01 +03:00
63b6786767
Minor
2022-10-10 22:06:27 +03:00
a53e06757f
Create README.md
2022-10-08 11:43:42 +03:00
0e3ba2f9fc
Adding dummy models for testing purposes
2022-10-08 11:43:42 +03:00
b0a11594ae
Initial release
2022-09-25 22:13:49 +03:00
