Whisper Small - Fine-tuned for Gujarati Speech-to-Text

This model is a fine-tuned version of openai/whisper-small for Gujarati transcription and translation tasks. It is capable of converting Gujarati speech into text, and since it is based on Whisper, it supports multilingual audio inputs. This fine-tuned model was specifically trained for improving performance on Gujarati speech data.

Model Details

Model Description

This model was fine-tuned on Gujarati speech data to improve transcription accuracy for audio recorded in Gujarati. It has been trained to handle diverse speech inputs, including variations in accents, backgrounds, and speech styles.

Developed by: [BLACK]
Shared by: [None]
Model type: Speech-to-Text (Fine-tuned Whisper Model)
Language(s): Gujarati
License: Apache-2.0
Finetuned from model: openai/whisper-small

Uses

Direct Use

import torch
import librosa
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq

processor = AutoProcessor.from_pretrained("iiBLACKii/Gujarati_VDB_Fine_Tune")
model = AutoModelForSpeechSeq2Seq.from_pretrained("iiBLACKii/Gujarati_VDB_Fine_Tune")

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

def preprocess_audio(file_path, sampling_rate=16000):
    audio_array, sr = librosa.load(file_path, sr=None)
    if sr != sampling_rate:
        audio_array = librosa.resample(audio_array, orig_sr=sr, target_sr=sampling_rate)
    return audio_array

def transcribe_and_translate_audio(audio_path):
    audio_array = preprocess_audio(audio_path)

    input_features = processor(audio_array, return_tensors="pt", sampling_rate=16000).input_features

    input_features = input_features.to(device)

    with torch.no_grad():
        predicted_ids = model.generate(input_features, max_length=400, num_beams=5)

    transcription_or_translation = processor.batch_decode(predicted_ids, skip_special_tokens=True)
    return transcription_or_translation[0]

if __name__ == "__main__":
    audio_file_path = ""   # .wav file path
    print("Transcribing and Translating audio...")
    result = transcribe_and_translate_audio(audio_file_path)
    print(f"Result: {result}")

Using Base Model (OpenAI)


import torch
import librosa
from transformers import WhisperProcessor, WhisperForConditionalGeneration, AutoConfig

repo_name = "iiBLACKii/Gujarati_VDB_Fine_Tune"

processor = WhisperProcessor.from_pretrained(repo_name)

config = AutoConfig.from_pretrained(repo_name)  

model = WhisperForConditionalGeneration.from_pretrained(repo_name, config=config)


device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

def preprocess_audio(file_path, sampling_rate=16000):
    audio_array, sr = librosa.load(file_path, sr=None)
    if sr != sampling_rate:
        audio_array = librosa.resample(audio_array, orig_sr=sr, target_sr=sampling_rate)
    return audio_array

def transcribe_audio(audio_path):
    audio_array = preprocess_audio(audio_path)

    input_features = processor.feature_extractor(
        audio_array, sampling_rate=16000, return_tensors="pt"
    ).input_features

    input_features = input_features.to(device)

    with torch.no_grad():
        predicted_ids = model.generate(
            input_features,
            max_new_tokens=400,  
            num_beams=5,  
        )

    transcription = processor.tokenizer.batch_decode(predicted_ids, skip_special_tokens=True)
    return transcription[0]

if __name__ == "__main__":
    audio_file_path = "" #.wav file path
    
    print("Transcribing audio...")
    transcription = transcribe_audio(audio_file_path)
    print(f"Transcription: {transcription}")

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 Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

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]