V3 audio transcription: aud.subarray is not a function about transformers.js HOT 8 CLOSED

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.

I saw this error once:

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'.

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.