coild/whisper_small_kannada

Whisper Small fine-tuned for Kannada

This is a Whisper Small model fine-tuned for Kannada Language on ~300 hrs of labeled dataset.

Performance

• Test WER: 29.63%
• Test CER: 7.12%
• Test WER WITH NORMALIZATION: 23.61%
• Test CER WITH NORMALIZATION: 6.21%

Usage

#!pip install whisper_transcriber 
from whisper_transcriber import WhisperTranscriber

# Initialize the transcriber
transcriber = WhisperTranscriber(model_name="coild/whisper_small_kannada")

# Transcribe an audio file with automatic transcript printing
results = transcriber.transcribe(
    "audio_file.mp3",
    min_segment=5,
    max_segment=15,
    silence_duration=0.2,
    sample_rate=16000,
    batch_size=4,
    normalize=True,
    normalize_text=True,
    verbose=False
)

# Access the transcription results manually
for i, segment in enumerate(results):
    print(f"\n[{segment['start']} --> {segment['end']}]")
    print(f"{segment['transcript']}")

Model Details

Model Description

• Developed by: Ranjan Shettigar
• Language(s) (NLP): kn
• Finetuned from model [OpenAI]: whipser-small

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Training Details

Training and evaluation data

Training Data:

• IISc-MILE Train Set Kannada ASR Corpus
• OpenSLR
• Google/Fleurs Train set

Evaluation Data:

• Google/Fleurs Test Set

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• optimizer: adamw
• epochs: 8

BibTeX:

[More Information Needed]