Model reference · open weights
wav2vec2-large-slavic-parlaspeech-hr is an open-weight audio or speech model from classla. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | classla |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Parameters (lead) | 315M |
| Runs with | transformers |
| Released | 2022-04-28 |
| Popularity | 552 downloads / month |
| Licence | Unknown |
About
This model for Croatian ASR is based on the facebook/wav2vec2-large-slavic-voxpopuli-v2 model and was fine-tuned with 300 hours of recordings and transcripts from the ASR Croatian parliament dataset ParlaSpeech-HR v1.0.
If you use this model, please cite the following paper:
Nikola Ljubešić, Danijel Koržinek, Peter Rupnik, Ivo-Pavao Jazbec. ParlaSpeech-HR -- a freely available ASR dataset for Croatian bootstrapped from the ParlaMint corpus. http://www.lrec-conf.org/proceedings/lrec2022/workshops/ParlaCLARINIII/pdf/2022.parlaclariniii-1.16.pdf
Evaluation is performed on the dev and test portions of the ParlaSpeech-HR v1.0 dataset.
| split | CER | WER |
|---|---|---|
| dev | 0.0311 | 0.0921 |
| test | 0.0222 | 0.0679 |
There are multiple models available, and in terms of CER and WER, the best-performing model is wav2vec2-large-slavic-parlaspeech-hr-lm.
transformersfrom transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
import soundfile as sf
import torch
import os
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# load model and tokenizer
processor = Wav2Vec2Processor.from_pretrained(
"classla/wav2vec2-large-slavic-parlaspeech-hr")
model = Wav2Vec2ForCTC.from_pretrained("classla/wav2vec2-large-slavic-parlaspeech-hr")
# download the example wav files:
os.system("wget https://huggingface.co/classla/wav2vec2-large-slavic-parlaspeech-hr/raw/main/00020570a.flac.wav")
# read the wav file
speech, sample_rate = sf.read("00020570a.flac.wav")
input_values = processor(speech, sampling_rate=sample_rate, return_tensors="pt").input_values.to(device)
# remove the raw wav file
os.system("rm 00020570a.flac.wav")
# retrieve logits
logits = model.to(device)(input_values).logits
# take argmax and decode
predicted_ids = torch.argmax(logits, dim=-1)
transcription = processor.decode(predicted_ids[0]).lower()
# transcription: 'veliki broj poslovnih subjekata posluje sa minusom velik dio'
In fine-tuning, the following arguments were used:
| arg | value |
|---|---|
per_device_train_batch_size | 16 |
gradient_accumulation_steps | 4 |
num_train_epochs | 8 |
learning_rate | 3e-4 |
warmup_steps | 500 |
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys wav2vec2-large-slavic-parlaspeech-hr for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (wav2vec2-large-slavic-parlaspeech-hr below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="wav2vec2-large-slavic-parlaspeech-hr" -F file=@audio.mp3
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.