py : make convert-pt-to-ggml.py backwards compatible with older vocab.json tokenizer files (#1001)

models : fix README.md (#964)

coreml : add support of large-v1 model (#926)

readme : add instructions on converting to GGML + "--no-config" to wget (#874)

minor : improve C++ and Python style (#768)

whisper : add Core ML support (#566)

models : change convert-pt-to-ggml to use .tiktoken tokenizer files (#725)

models : handle spaces and special characters in shell script paths (#677)

models : change default encoding to utf8 (#605)

models : change HF hosting from dataset to model

models : fix HF model URL (close #356)

models : fix typo in convert-h5-to-ggml.py

models : fix support for spaces in path (close #315)

talk : improve prompting

Fix paths echoed after the download

models : add the new "large" model release by OpenAI

talk.wasm : move to https://whisper.ggerganov.com/talk

models : add instructions for using HF fine-tuned models

models : add usage comments to the HF convert script (#157)

models : fix HF fine-tuned model conversion script (#157)

models : minor changes to the HF convert script (#157)

models : add "convert-h5-to-ggml.py" script (#157)

models : simplify the conversion script

Update download-ggml-model.sh

models : change default hosting to Hugging Face

minor : remove one more redundant line

minor : fix double float32 conversion in python script

extra : compute SHA of all models files

Added for Windows implemenated script download-ggml-model.cmd

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.

refactoring : move main + stream in examples + other stuff

Add enconding parameter to vocab.json opening to fix errors

Update README.md and finalize the whisper.wasm example

Minor

Create README.md

Adding dummy models for testing purposes

Initial release