Comments (5)
-
You are right, the examples in
genset_examples.tsv
is not produced byprepare_phn2ltr_librilm.sh
. (Actuallyprepare_phn2ltr_librilm.sh
is organized ONLY for producing phone-letter data for pre-training SpeechLM-P model.)
The difference is: The T2U generator uses 41 mono phones, while SpeechLM-P model uses 300+ word-position-dependent phones. (The former can be easily merged to the latter by Kaldi. This inconsistency is just due to the division of work among different people.) -
The phonemes for the T2U generator are not up-sampled, because the T2U generator will predict the duration information. The probability of inserting silence was indeed set to 0.25. Note that the probability is "silence between words" instead of "silence between phones", so when you calculate the phones' probability, it is less than 0.25.
-
To prepare the phoneme sequence for the inference of the T2U generator, please use
speechlm/data_process/phoneize_with_sil.py
, with the input of a word-level text and a word-to-phone lexicon (see readme.md). e.g.
python speechut/data_process/phoneize_with_sil.py -i librilm.wrd -o librilm.phn --lexicon lexicon.lst --surround -s 0.25
Hope the above information could help you.
from speecht5.
Thanks a lot, that is really helpful. But I have another question.
Phonemes need to be converted to idx (eg. AH B -> 1 2
). This step is achieved through the vocabulary dict.PHN.txt
. Would you mind sharing this PHN2phh vocabulary? dataset/LibriSpeech/fast_phone2unit
only contains dict.km.txt
and dict.phn.txt
, which is not enough for generating genset_examples.tsv
.
from speecht5.
Thanks a lot, that is really helpful. But I have another question. Phonemes need to be converted to idx (eg.
AH B -> 1 2
). This step is achieved through the vocabularydict.PHN.txt
. Would you mind sharing this PHN2phh vocabulary?dataset/LibriSpeech/fast_phone2unit
only containsdict.km.txt
anddict.phn.txt
, which is not enough for generatinggenset_examples.tsv
.
I think The CMU Pronouncing Dictionary is required. There are no more questions.
from speecht5.
Sorry for the late response. dataset/LibriSpeech/fast_phone2unit
contains both dict.PHN.txt
and dict.phn.txt
, which stand for symbol and idx respectively. The two files are aligned line by line (e.g. the same line in two files means the same phones). So I think they are sufficient to convert the phone symbols generated by speechut/data_process/phoneize_with_sil.py
to numerical IDs.
from speecht5.
I found out why I can not find both dict.phn.txt
and dict.PHN.txt
in dataset/LibriSpeech/fast_phone2unit
.
This is because the suffix of the windows system is not case sensitive (dict.phn.txt
and dict.PHN.txt
are the same). When I download the code and unzip it on windows system, overwriting happens, but this problem does not happen on linux system.
Thanks again for your response. I have reproduced the T2U generator successfully.
from speecht5.
Related Issues (20)
- VATLM: Error when loading finetuned checkpoints for infer_s2s
- pretrain loss HOT 4
- Getting TTS output voice close to the training data - Finetuning on different language HOT 2
- Voice Conversion - Error with Some Mono, 16kHz, 16bit Audio HOT 2
- Reproduce ASR experiment results in Hugging Face
- Generate the N-best (top few) hypotheses
- Is end-to-end S2ST possible with Speecht5?
- ASR SpeechT5 training - model predicts same output for different inputs
- SpeechT5 - TTS - Tokenizer adding `▁` token between newly added Vietnamese characters HOT 1
- The size of tensor a (674) must match the size of tensor b (600) at non-singleton dimension 1 HOT 1
- 是否支持中文转语音? HOT 4
- How to setting language when do S2T HOT 1
- Baseline implementation HOT 1
- Text feature extraction using SpeechLM
- British English TTS model HOT 1
- "SpeechT5" on Android OS
- Link to train_960.tsv is broken
- What is the time taken to converge for the hidden unit tokenizer?
- Does the pre-trained model for hidden unit tokenizer use speaker embeddings?
- extract transorformer layer feature 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 speecht5.