Skip to main content
The 2026 Annual Developer Survey is live— take the Survey today!
53 questions
Newest Active Bountied Unanswered
Score of 0
0 answers
431 views

WE are using Montreal Forced Aligner (MFA) 3.x to train an acoustic model on a large dataset (~33GB of audio and transcripts in an Indian language). The training process takes an extremely long time(...
Score of 0
0 answers
625 views

How would I easily convert English audio files to IPA (phonetic alphabet) with time stamps on Windows? Everything I find is way out of date. Even similar questions here on stack are out of date. Most ...
Score of 4
1 answer
7198 views

Using a microphone as an input for real-time audio. How do I extract the currently said phoneme from the audio? I need it for lipsyncing 2d characters. Basically, my approach would be to: Fetch the ...
Score of 1
0 answers
106 views

I have audio files from a bilingual speaker (who speaks German and Turkish). I am trying to get the phoneme level annotation for the same using MFA. Is there anyway I can get accurate outputs? I am ...
Score of -1
1 answer
736 views

e.g. let's assume we have something like: WOULD | YOU | LIKE | A | CUP | OF | TEA w ʊ d | j uː | l a ɪ k | ə | k ʌ p | ʊ v | t iː W UH D | Y UW | L AY K | AH | K AH P | AH V | T IY And ...
Score of 1
0 answers
270 views

I am using the SpeechBrain model to predict phoneme sequences based on the audio data. The output of the model is like this, ['sil', 'dh', 'ih', 'r', 'iy', 'z', 'ah', 'n', 'z', 'f', 'er', 'dh', 'ih', ...
Score of 0
1 answer
103 views

The code doesn't need to be exactly correct. A pronunciation in English can be used to represent a similar pronunciation in Chinese, e.g. /ʈ͡ʂ/ can use "CH" to represent.
Score of 0
0 answers
74 views

I'm trying to create a string subclass, in order to represent Arpabet symbols as single characters. Here is what I got so far: import Levenshtein class ArpabetChar(str): """ Class that ...
Score of 1
2 answers
2384 views

I am following the Google Cloud API Text-to-Speech Python tutorial. I would like to know if there is a way to return the phonemes and their duration, an intermediate step in generating the interpreted ...
Score of 1
0 answers
32 views

I fine-tuned a dataset of Nvidia Tacotron2. While working reasonably well, there are some mispronounciations of words(I train a german dataset). I have another set of wave files by the same speaker ...
Score of 1
1 answer
54 views

I have a little problem with my JsonStream in C# I am reading a Json Blob in my Storage with this inside: {"id":"275177", "fremdwort":"1.FFC-Frankfurt", "...
Score of 0
1 answer
158 views

We need to build a custom model with a lot of already phonemically transcribed custom vocabulary, but the current API for specifying custom words has no published option for specifying a phonemic ...
Score of -4
1 answer
333 views

I was wondering if anyone knows of a python tool that finds phonemes from a text, as well as their duration. In short, I want a forced alignment tool like aeneas, but I want the phonemes and their ...
Score of 0
1 answer
623 views

I could successfully extract phoneme data from an audio file using Pocketsphinx, but how can I also output the lasting time of each phoneme? def phonemes(filename): audio_path = os.path.join(...
Score of 0
0 answers
307 views

It is possible to extract the default phonemes for a given word via SAPI by: Voice word with text-to-speech and store output in a .wav Use the .wav as input for speech recognition Upon recognition of ...

15 30 50 per page
1
2 3 4