whisper-s2t-blockifier

Transcribe audio with OpenAI's Whisper. Just upload audio to Steamship and apply this Blockifier.

Using

Tagger Plugins add annotations to text that can be queried and composed later.

Blockifiers convert data into Steamship’s native Block format.

Importer Plugins add annotations to text that can be queried and composed later.

Use them when writing Packages to help you work with data of different types.

Links

from steamship import Steamship, File

client = Steamship(workspace="my-workspace-handle")

# Import a file to Steamship
with open("file.ext") as f:
  file = File.create(content=file.read())

# Create an instance of this blockifier
blockifier = client.use_plugin(
  'whisper-s2t-blockifier'
)

# Blockify the file
task = file.blockify()
task.wait()
from steamship import Steamship, File

client = Steamship(workspace="my-workspace-handle")

# Import a file to Steamship
with open("file.ext") as f:
  file = File.create(content=file.read())

# Create a blockifier. We'll assume Markdown here.
blockifier = client.use_plugin(
  'markdown-blockifier-default'
)

# Blockify the file
task = file.blockify()

# Create an instance of this tagger.
tagger = client.use_plugin(
  'whisper-s2t-blockifier'
)

# Tag the file
task = file.tag()

task.wait()
Pulled from the GitHub repository.
# Whisper Transcribe blockifier

This project contains a Steamship Blockifier that transcribes audio files via Whisper.

## Configuration

This plugin is configured using an API key and a model key for the backend that is running the Whisper model. Those keys
are supplied via secrets.

## Getting Started

### Usage

To authenticate with Steamship, install the Steamship CLI with:

```bash
> npm install -g @steamship/cli
```

And then login with:

```bash
> ship login
```

```python
from steamship import Steamship, File, MimeTypes

workspace = Steamship(workspace="whisper-s2t-plugin-demo-001")
plugin_config = {"get_segments": True, "whisper_model": "tiny"}
whisper = workspace.use_plugin("whisper-s2t-blockifier", "whisper-instance-0001", config=plugin_config)

audio_path = "FILL_IN"
file = File.create(whisper.client, content=audio_path.open('rb').read(), mime_type=MimeTypes.MP3)
blockify_response = file.blockify(plugin_instance=whisper.handle)
blockify_response.wait(max_timeout_s=3600, retry_delay_s=1)

file = file.refresh()

for block in file.blocks:
    print(block.text)
```

## Developing

Development instructions are located in [DEVELOPING.md](https://github.com/steamship-plugins/whisper-s2t-blockifier/blob/main/DEVELOPING.md)

## Testing

Testing instructions are located in [TESTING.md](https://github.com/steamship-plugins/whisper-s2t-blockifier/blob/main/TESTING.md)

## Deploying

Deployment instructions are located in [DEPLOYING.md](https://github.com/steamship-plugins/whisper-s2t-blockifier/blob/main/DEPLOYING.md)

Steamship is building the fastest way to ship language AI.

Stop building and start shipping. Reach out to get onboarded.
Read More