Does anyone know why the WER does not decay? I'm fine tuning the openai whisper medium model for low resource language?
(https://i.stack.imgur.com/4bmPl.png)
per_device_train_batch_size="32"
per_device_eval_batch_size="16"
learning_rate="1e-5"
OpenAI whisper medium WER does not decay for low resource language
69 Views Asked by Apple Son At
0
There are 0 best solutions below
Related Questions in OPENAI-API
- Scrimba tutorial was working, suddenly stopped even trying the default
- How to return HTTP Get request response from models class in Django project
- Protect OpenAI key using Firebase function
- Python ChatGPT bot issue with openai.Completion
- How do I send an audio file to OpenAi?
- Fine-Tuning Large Language Model on PDFs containing Text and Images
- Error Accessing completions Property of openai in Node.js Module
- LangChain OpenAI Agent with Sources
- Azure openai load testing mode
- how to add the button onto the furnace GUI in minecraft
- How can I use open ai api key for my tic tac toe game
- Getting an error while using the open ai api to summarize news atricles
- How to integrate source section in chat gpt API in py?
- Why does this error keep showing, what am i missing? await message.channel.send(f"Answer: {bot_response}") IndentationError: unexpected indent
- How do I embed json documents using embedding models like sentence-transformer or open ai's embedding model?
Related Questions in OPENAI-WHISPER
- using whisper in the terminal gives an error
- How to improve Whisper speech to text
- Unable to install ‘audio.whisper’ package from GitHub in RStudio despite correct Rtools installation
- Error: Cannot set headers after they are sent to the client && Error in getTranscript: AxiosError: Request failed with status code 400
- load local model using `WhisperForConditionalGeneration` class
- TranscriptionOptions.__new__() missing 3 required positional arguments: 'max_new_tokens', 'clip_timestamps', and 'hallucination_silence_threshold'
- How to optimise Hyperparameters for Whisper finetuning?
- Can't load Tokenizer using hugging-face whisper and gradio
- Can openAI Whisper recognize audio at specified frequencies?
- Can Distilled Whisper Models be used as a Drop-In Replacement for OpenAI Whisper?
- Making a Moviepy video and saving it to an S3 with python flask
- Huggingface Seq2seqTrainer freezes on evaluation
- replace whisper tokenizer with BERT tokenizer
- Faster Whisper float 16 issue
- WinError 2 The system cannot find the file specified
Related Questions in WHISPER
- Inference question through LoRA in Whisper model
- How to solve AttributeError: 'Audio' object has no attribute 'transcribe'?
- Can openAI Whisper recognize audio at specified frequencies?
- Sending axios request to Whisper endpoint with file input in client-side JS
- When using whisper-node, it blocks the rest of the requests in nest.js
- MySQL OperationalError 2006 with FastAPI and SQLAlchemy during audio file upload
- Whisper neural network how to set up two-channel recognition?
- convert a whisper-small.pt model to hugging face through convert_openai_to_hf.py
- FileNotFoundError: [WinError 2] The system cannot find the specified file (Trying make a AI voice assistant)
- How can I run a python github project to my nodejs project?
- Azure openai speech to text -Whisper "code":"404","message": "Resource not found"
- how can i send telegram voice file to whisper effective and correct?
- Exception has occurred: TypeError argument of type 'NoneType' is not iterable - When importing whisper
- How to use ZLUDA for whisper?
- OpenAI whisper medium WER does not decay for low resource language
Trending Questions
- UIImageView Frame Doesn't Reflect Constraints
- Is it possible to use adb commands to click on a view by finding its ID?
- How to create a new web character symbol recognizable by html/javascript?
- Why isn't my CSS3 animation smooth in Google Chrome (but very smooth on other browsers)?
- Heap Gives Page Fault
- Connect ffmpeg to Visual Studio 2008
- Both Object- and ValueAnimator jumps when Duration is set above API LvL 24
- How to avoid default initialization of objects in std::vector?
- second argument of the command line arguments in a format other than char** argv or char* argv[]
- How to improve efficiency of algorithm which generates next lexicographic permutation?
- Navigating to the another actvity app getting crash in android
- How to read the particular message format in android and store in sqlite database?
- Resetting inventory status after order is cancelled
- Efficiently compute powers of X in SSE/AVX
- Insert into an external database using ajax and php : POST 500 (Internal Server Error)
Popular Questions
- How do I undo the most recent local commits in Git?
- How can I remove a specific item from an array in JavaScript?
- How do I delete a Git branch locally and remotely?
- Find all files containing a specific text (string) on Linux?
- How do I revert a Git repository to a previous commit?
- How do I create an HTML button that acts like a link?
- How do I check out a remote Git branch?
- How do I force "git pull" to overwrite local files?
- How do I list all files of a directory?
- How to check whether a string contains a substring in JavaScript?
- How do I redirect to another webpage?
- How can I iterate over rows in a Pandas DataFrame?
- How do I convert a String to an int in Java?
- Does Python have a string 'contains' substring method?
- How do I check if a string contains a specific word?