🏗️ Building on HF

manasseh

manassehzw

https://manasseh.dev

AI & ML interests

Voice Models, TTS, Conversational AI, GPT

Recent Activity

liked a model 10 days ago

Zyphra/ZONOS2

liked a model 13 days ago

bosonai/higgs-audio-v3-tts-4b

liked a model 16 days ago

k2-fsa/OmniVoice

View all activity

Organizations

None yet

liked a model 10 days ago

Zyphra/ZONOS2

Text-to-Speech • Updated about 12 hours ago • 1.1k • 124

liked a model 13 days ago

bosonai/higgs-audio-v3-tts-4b

Text-to-Speech • 5B • Updated 7 days ago • 78.7k • 514

liked a model 16 days ago

k2-fsa/OmniVoice

Text-to-Speech • 0.6B • Updated May 7 • 1.47M • 1.06k

updated a model about 1 month ago

manassehzw/sna-parakeet-tdt-0.6b-v3

Automatic Speech Recognition • Updated May 14 • 35

published a model about 1 month ago

manassehzw/sna-parakeet-tdt-0.6b-v3

Automatic Speech Recognition • Updated May 14 • 35

updated a model about 2 months ago

manassehzw/sna-f5-tts

Text-to-Speech • 0.3B • Updated May 7 • 288 • 1

updated a dataset about 2 months ago

manassehzw/sna-manasseh-150-raw

Viewer • Updated May 2 • 150 • 24

published a dataset about 2 months ago

manassehzw/sna-manasseh-150-raw

Viewer • Updated May 2 • 150 • 24

updated a model about 2 months ago

manassehzw/sna-tts-v1

36.3M • Updated May 1 • 4 • 1

published a model about 2 months ago

manassehzw/sna-tts-v1

36.3M • Updated May 1 • 4 • 1

replied to yuriyvnv's post 2 months ago

Thank you! this is a huge help, let me play around with the repo and see what results i can get. I'll definitely reach out if i need any other assistance.

reacted to yuriyvnv's post with 🚀 2 months ago

Post

639

🎙️Parakeet-TDT Fine Tuning: 4 New ASR Models

Four fine-tuned versions of NVIDIA's Parakeet-TDT-0.6B-v3 for Dutch, Portuguese, Estonian, and Slovenian — among the first community fine-tunes of this architecture for the aforementioned languages

📊 Results on Common Voice 17 test sets:

🇸🇮 Slovenian: 50.49% → 11.56% WER (-77%)
🇵🇹 Portuguese: 15.86% → 10.71% WER (-32%)
🇪🇪 Estonian: 27.15% → 21.03% WER (-23%)
🇳🇱 Dutch: 5.99% → 5.33% WER (-11%)

All models output cased text with punctuation.

import nemo.collections.asr as nemo_asr

model = nemo_asr.models.ASRModel.from_pretrained(
    "yuriyvnv/parakeet-tdt-0.6b-dutch"
)
output = model.transcribe(["audio.wav"])
print(output[0].text)

🔗 Models:
🇳🇱 yuriyvnv/parakeet-tdt-0.6b-dutch
🇵🇹 yuriyvnv/parakeet-tdt-0.6b-portuguese
🇪🇪 yuriyvnv/parakeet-tdt-0.6b-estonian
🇸🇮 yuriyvnv/parakeet-tdt-0.6b-slovenian

🏗️ Training: Common Voice 17 + synthetic speech (OpenAI TTS), filtered with WAVe (yuriyvnv/WAVe-1B-Multimodal-PT) for quality. AdamW + cosine annealing, bf16-mixed precision, early stopping on val WER. Timestamps and long-form audio supported.

@hf-audio @NVIDIADev

#asr #speech #parakeet #nvidia #nemo #multilingual #fine-tuning #commonvoice

3 replies

replied to yuriyvnv's post 2 months ago

Amazing, impressive work!

I’m interested in fine-tuning Parakeet for low-resource African languages. could not find any NVIDIA fine-tuning guide yet, would you be open to sharing any pointers on your training setup, workflow, or resources you found helpful?