---
library_name: transformers
tags: [speech-to-text, transcription, Gujarati, whisper, fine-tuned]
---

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

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/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](https://huggingface.co/openai/whisper-small)


## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

```python
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)
```python

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]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

[More Information Needed]

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

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

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

### Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->

#### Preprocessing [optional]

[More Information Needed]


#### Training Hyperparameters

- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->

#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->

[More Information Needed]

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Testing Data, Factors & Metrics

#### Testing Data

<!-- This should link to a Dataset Card if possible. -->

[More Information Needed]

#### Factors

<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->

[More Information Needed]

#### Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

[More Information Needed]

### Results

[More Information Needed]

#### Summary



## Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **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]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]

## Glossary [optional]

<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->

[More Information Needed]

## More Information [optional]

[More Information Needed]

## Model Card Authors [optional]

[More Information Needed]

## Model Card Contact

[More Information Needed]