Skip to content

Commit

Permalink
Update Dockerfile, README.md, and 5 more files...
Browse files Browse the repository at this point in the history
  • Loading branch information
lkmeta committed Jan 11, 2025
1 parent 85a9bd9 commit 4e4a861
Show file tree
Hide file tree
Showing 7 changed files with 8 additions and 19 deletions.
2 changes: 1 addition & 1 deletion Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ ENV PATH="/root/.local/share/pypoetry/venv/bin:$PATH"
# Preload the model to avoid loading it on the first request
# Note: Keep in mind that this will increase the image size and build time
# Choose the model you want to preload (e.g., openai/whisper-medium)
RUN test -d /root/.cache/huggingface || poetry run python -c "from transformers import AutoModelForSpeechSeq2Seq; AutoModelForSpeechSeq2Seq.from_pretrained('openai/whisper-medium')"
# RUN test -d /root/.cache/huggingface || poetry run python -c "from transformers import AutoModelForSpeechSeq2Seq; AutoModelForSpeechSeq2Seq.from_pretrained('openai/whisper-medium')"

# Expose port 8010
EXPOSE 8010
Expand Down
12 changes: 1 addition & 11 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@
</p>
</div>

Txtify is a free open-source web application that transcribes and translates audio from YouTube videos or uploaded media files. It now runs on Docker for easier deployment and includes monitoring capabilities. Leveraging the **`stable-ts`** library and the **`whisper-medium`** model, Txtify offers enhanced transcription accuracy and performance.
Txtify is a free open-source web application that transcribes and translates audio from YouTube videos or uploaded media files. It now runs on Docker for easier deployment and includes monitoring capabilities. Leveraging the **`stable-ts`** library and the **`whisper`** models, Txtify offers enhanced transcription accuracy and performance.

## Table of Contents

Expand All @@ -40,7 +40,6 @@ Txtify is a free open-source web application that transcribes and translates aud

Txtify is designed to simplify the process of converting audio and video content into text. Whether you're looking to transcribe a YouTube video or your own audio/video files, Txtify offers an easy-to-use interface and powerful AI models to ensure accuracy and speed. The application supports multiple output formats including `.txt`, `.srt`, `.vtt`, and `.sbv`.


## Demo

<div align="center">
Expand Down Expand Up @@ -79,9 +78,6 @@ cp .env.example .env
3. Run the Docker

> <sub>**Note:** The **whisper-medium** model is pre-selected and downloaded during the Docker build process. This ensures faster and more efficient transcriptions without the need to download the model each time.</sub>

```sh
docker-compose up --build -d
```
Expand All @@ -94,12 +90,6 @@ docker-compose up --build -d
docker-compose down
```

### **Why whisper-medium?**

- **Enhanced Performance:** The **whisper-medium** model offers a balanced trade-off between speed and accuracy, making it ideal for a wide range of transcription tasks.
- **Pre-downloading:** By downloading the model during the Docker image build, you avoid the overhead of fetching it at runtime, leading to quicker startup times and a smoother user experience.


## Usage

### Access the Application
Expand Down
2 changes: 1 addition & 1 deletion src/main.py
Original file line number Diff line number Diff line change
Expand Up @@ -132,7 +132,7 @@ async def submit_contact(
<p><strong>Message:</strong></p>
<blockquote>{message}</blockquote>
<div class="footer">
&copy; 2025 Txtify. Created by <a href="https://lkmeta.me" target="_blank">lkmeta</a>.
&copy; 2025 Txtify. Created by <a href="https://lkmeta.com" target="_blank">lkmeta</a>.
</div>
</div>
</body>
Expand Down
2 changes: 1 addition & 1 deletion templates/contact.html
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@ <h2>Stay Updated</h2>

<div class="footer">
&copy; 2025 Txt<span style="color: var(--primary-color);">ify</span>. Created with <i
class="fa-solid fa-heart heart"></i> by <a href="https://lkmeta.me" target="_blank">lkmeta</a>.
class="fa-solid fa-heart heart"></i> by <a href="https://lkmeta.com" target="_blank">lkmeta</a>.
</div>

<!-- Alert Box Structure -->
Expand Down
2 changes: 1 addition & 1 deletion templates/error.html
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ <h1>404 - Page Not Found</h1>
</div>
<div class="footer">
&copy; 2025 Txt<span style="color: var(--primary-color);">ify</span>. Created with <i
class="fa-solid fa-heart heart"></i> by <a href="https://lkmeta.me" target="_blank">lkmeta</a>.
class="fa-solid fa-heart heart"></i> by <a href="https://lkmeta.com" target="_blank">lkmeta</a>.
</div>

<script src="/static/scripts.js"></script>
Expand Down
2 changes: 1 addition & 1 deletion templates/faq.html
Original file line number Diff line number Diff line change
Expand Up @@ -235,7 +235,7 @@ <h2>Contact</h2>

<div class="footer">
&copy; 2025 Txt<span style="color: var(--primary-color);">ify</span>. Created with <i
class="fa-solid fa-heart heart"></i> by <a href="https://lkmeta.me" target="_blank">lkmeta</a>.
class="fa-solid fa-heart heart"></i> by <a href="https://lkmeta.com" target="_blank">lkmeta</a>.
</div>


Expand Down
5 changes: 2 additions & 3 deletions templates/index.html
Original file line number Diff line number Diff line change
Expand Up @@ -113,8 +113,7 @@ <h1>Audio and Video to Text for FREE using AI</h1>
<option value="whisper_base" selected>Whisper Base (Fast - Balanced - English Only)</span>
</option>
<option value="whisper_small">Whisper Small (Fast - Accurate - English Only)</option>
<option value="whisper_medium">Whisper Medium (Fast - High Accuracy - Multi-Language - Downloaded by
Default - RECOMMENDED)</option>
<option value="whisper_medium">Whisper Medium (Fast - High Accuracy - Multi-Language - RECOMMENDED)</option>
</option>
<option value="whisper_large">Whisper Large (Slow - Highest Accuracy - Multi-Language)
</option>
Expand Down Expand Up @@ -160,7 +159,7 @@ <h1>Audio and Video to Text for FREE using AI</h1>
</div>
<div class="footer">
&copy; 2025 Txt<span style="color: var(--primary-color);">ify</span>. Created with <i
class="fa-solid fa-heart heart"></i> by <a href="https://lkmeta.me" target="_blank">lkmeta</a>.
class="fa-solid fa-heart heart"></i> by <a href="https://lkmeta.com" target="_blank">lkmeta</a>.
</div>


Expand Down

0 comments on commit 4e4a861

Please sign in to comment.