Comments (8)
FP32 was the key
from transformers.js.
Nah, no worries. With what you're saying I believe the issue was that I was feeding it a fake array to get it to preload. That worked with the V2 version, but no longer worked with the V3 version. But that's fine as there are plenty of new ways to handle pre-loading.
from transformers.js.
I spotted a small typo in the demo:
PipelineSingeton
is missing an L
from transformers.js.
A small question: is there a downside to simply always using the timestamp version?
from transformers.js.
And some more questions:
The V2 demo has a number of values that could be manipulated. Are they still useful?
- const isDistilWhisper = model.startsWith("distil-whisper/");
- quantized
and these:
/// Greedy
//top_k: 0,
//do_sample: false,
// Sliding window
//chunk_length_s: isDistilWhisper ? 20 : 30,
//stride_length_s: isDistilWhisper ? 3 : 5,
// Language and task
//language: language,
task: subtask,
// Return timestamps
//return_timestamps: true,
//force_full_sequences: false,
from transformers.js.
from transformers.js.
I'm having some trouble getting it to respond with more than 1 word when using WebGPU. It usually thinks it heard 'And'.
![Screenshot 2024-07-11 at 01 07 14](https://private-user-images.githubusercontent.com/805405/347628016-1ab1f6a1-b75d-4101-8a19-6d93461ce2b1.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjIyMjM4NTcsIm5iZiI6MTcyMjIyMzU1NywicGF0aCI6Ii84MDU0MDUvMzQ3NjI4MDE2LTFhYjFmNmExLWI3NWQtNDEwMS04YTE5LTZkOTM0NjFjZTJiMS5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNzI5JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDcyOVQwMzI1NTdaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1lMTNkM2U5Y2JhODAxMTgzYTFmOTk4MWMzNDJhMWQzNjcxNzhkZDY2ZjZiZjQ2MzQ5ZDc4N2YxM2IyZTU3ZWVkJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.mP8nJTDKcZxSBs88n1d2QLKfaoe6_Tj1lWcfTaHou1s)
from transformers.js.
Thanks for the report! The function does require Float32Array
or Float64Array
inputs, but we could use .slice()
if .subarray
isn't present (for normal arrays)
from transformers.js.
Related Issues (20)
- range error: array buffer allocation failed <- how to catch this error?
- transformers@latest: Unsupported model IR version: 9, max supported IR version: 8 HOT 1
- Support nomic-ai/nomic-embed-vision-v1.5 HOT 1
- AutoModel.from_pretrained - Which model is loaded HOT 1
- The scripts/convert.py script fails for a few reasons HOT 1
- RAGatouille/Colbert support
- Result is wrong when decoding tokens one by one HOT 1
- How do you delete a downloaded model? HOT 2
- Support for Both Word-Level and Sentence-Level Timestamps in ASR Decoding
- Segmentation fault while converting Bert-base-uncased with README command HOT 2
- Can't run depth-anything-v2 HOT 1
- Support for react-native
- JavaScript code completion model
- [Severe] Memory leak issue under WebGPU Whisper transcribe pipeline
- 4bit ONNX models support HOT 1
- how to retain spiece token markers HOT 2
- No loader is configured for ".node" files
- musicgen example run error on lastest v3
- compat with transformers >= 4.40 and tokenizers >= 0.19 HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from transformers.js.