loko99/whisper_small_kannada

Whisper Small fine-tuned for Kannada ASR

This is a Whisper Small model fine-tuned for Kannada automatic speech recognition (ASR). The model was trained on a custom Kannada dataset.

Performance

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

Usage

from transformers import pipeline, WhisperForConditionalGeneration, WhisperTokenizer, WhisperFeatureExtractor

model = WhisperForConditionalGeneration.from_pretrained("loko99/whisper_small_kannada_v2")
tokenizer = WhisperTokenizer.from_pretrained("loko99/whisper_small_kannada_v2", language="kannada", task="transcribe")
feature_extractor = WhisperFeatureExtractor.from_pretrained("loko99/whisper_small_kannada_v2")

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=tokenizer,
    feature_extractor=feature_extractor,
    chunk_length_s=30,
    device="cuda" # use "cpu" if you don't have a GPU
)

# Transcribe audio
result = pipe("path/to/audio.wav")
print(result["text"])

Model Details

Model Description

• Developed by: [More Information Needed]
• Funded by [optional]: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): kn
• Finetuned from model [optional]: [More Information Needed]

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

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[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

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]