speech_recognition
speech_recognition copied to clipboard
Uberi
Speech recognition module for Python, supporting several engines and APIs, online and offline.
Feature request: Add a recognizer for Whisper from here: https://github.com/openai/whisper I'll start a PR.
Steps to reproduce ------------------ 1. On smaller models, the `Recognizer.recognize_vosk` method is pretty fast, but when I use a bigger model, it slows down significantly. 2. I copy paste the...
* Don't depend on the internal `pocketsphinx.pocketsphinx` module * Point the documentation to the right place. **NOTE**: `--pre` is added to the `pip` command-line since PocketSphinx 5 is still pre-release,...
Hello, I am building an assistant with the following behavior: - speech_recognition with Sphinx locally listen in background and wait for a wake-up word - after that I record some...
In November OpenAI released version 1.0 that deprecated a lot of old API. These changes addresses issues raised in #720 and fixes now completely broken `recognize_whisper_api` API.
We would like to contribute support for the AssemblyAI transcript APIs. It's a little unclear if this project is still maintained, and if contributions are accepted. If it still is,...
Feature Requested ------------------ Add parameters `use_enhanced` and `model` to the `recognize_google_cloud` method to set their respective values in the RecognitionConfig Expected behaviour ------------------ Give more customizable options for the user...
Adds the parameters use_enhanced and model to the recognize_google_cloud method for more customizable options for the user and better results in specific cases
When using Google cloud speech, there remains TimeoutError: [WinError 10060] or ConnectionAbortedError: [WinError 10053]. How to solve this problem?
Steps to reproduce ------------------ 1.The issue happen every time i run the code [WinError 10054] An existing connection was forcibly closed by the remote host 2. Every time i run...
