metadata

language_bcp47:
  - kn-IN
model-index:
  - name: Whisper Small Kannada
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: google/fleurs
          type: google/fleurs
          config: kn_in
          split: test
        metrics:
          - type: wer
            value: 29.63
            name: WER
          - type: cer
            value: 7.12
            name: CER
          - type: wer
            value: 23.61
            name: WER WITH NORMALIZATION
          - type: cer
            value: 6.21
            name: CER WITH NORMALIZATION
pipeline_tag: automatic-speech-recognition
language:
  - kn
metrics:
  - wer
base_model:
  - openai/whisper-small
library_name: transformers

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:

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]