w2v-bert-2.0-kbd-v2

Circassian (Kabardian) ASR Model

This is a fine-tuned model for Automatic Speech Recognition (ASR) in kbd, based on the facebook/w2v-bert-2.0 model.

The model was trained on a combination of the anzorq/kbd_speech (filtered on country=russia) and anzorq/sixuxar_yijiri_mak7 datasets.

Model Details

• Base Model: facebook/w2v-bert-2.0
• Language: Kabardian
• Task: Automatic Speech Recognition (ASR)
• Datasets: anzorq/kbd_speech, anzorq/sixuxar_yijiri_mak7
• Training Steps: 4000

Training

The model was fine-tuned using the following training arguments:

TrainingArguments(
   output_dir='output',
   group_by_length=True,
   per_device_train_batch_size=8,
   gradient_accumulation_steps=2,
   evaluation_strategy="steps",
   num_train_epochs=10,
   gradient_checkpointing=True,
   fp16=True,
   save_steps=1000,
   eval_steps=500,
   logging_steps=300,
   learning_rate=5e-5,
   warmup_steps=500,
   save_total_limit=2,
   push_to_hub=True,
   report_to="wandb"
)

Performance

The model's performance during training:

Note

To optimize training and reduce tokenizer vocabulary size, prior to training the following digraphs in the training data were replaced with single characters:

гъ -> ɣ
дж -> j
дз -> ӡ
жь -> ʐ
кӏ -> қ
къ -> q
кхъ -> qҳ
лъ -> ɬ
лӏ -> ԯ
пӏ -> ԥ
тӏ -> ҭ
фӏ -> ჶ
хь -> h
хъ -> ҳ
цӏ -> ҵ
щӏ -> ɕ
я  -> йа

After obtaining the transcription, reversed replacements can be applied to restore the original characters.

Inference

import torchaudio
from transformers import pipeline

pipe = pipeline(model="anzorq/w2v-bert-2.0-kbd-v2", device=0)

reversed_replacements = {
    'ɣ': 'гъ', 'j': 'дж', 'ӡ': 'дз', 'ʐ': 'жь',
    'қ': 'кӏ', 'q': 'къ', 'qҳ': 'кхъ', 'ɬ': 'лъ',
    'ԯ': 'лӏ', 'ԥ': 'пӏ', 'ҭ': 'тӏ', 'ჶ': 'фӏ',
    'h': 'хь', 'ҳ': 'хъ', 'ҵ': 'цӏ', 'ɕ': 'щӏ',
    'йа': 'я'
}

def reverse_replace_symbols(text):
    for orig, replacement in reversed_replacements.items():
        text = text.replace(orig, replacement)
    return text

def transcribe_speech(audio_path):
    waveform, sample_rate = torchaudio.load(audio_path)
    waveform = torchaudio.transforms.Resample(orig_freq=sample_rate, new_freq=16000)(waveform)
    torchaudio.save("temp.wav", waveform, 16000)
    transcription = pipe("temp.wav", chunk_length_s=10)['text']
    transcription = reverse_replace_symbols(transcription)
    return transcription

audio_path = "audio.wav"
transcription = transcribe_speech(audio_path)
print(f"Transcription: {transcription}")