Merge pull request #62 from deepgram/synchronous-prerecorded

Adding new feature non-async prerecorded

README.md

@@ -19,6 +19,28 @@ pip install deepgram-sdk
 
 #### Transcribe an Existing File or Pre-recorded Audio
 
+```python
+from deepgram import Deepgram
+import json
+
+DEEPGRAM_API_KEY = 'YOUR_API_KEY'
+PATH_TO_FILE = 'some/file.wav'
+
+def main():
+    # Initializes the Deepgram SDK
+    deepgram = Deepgram(DEEPGRAM_API_KEY)
+    # Open the audio file
+    with open(PATH_TO_FILE, 'rb') as audio:
+        # ...or replace mimetype as appropriate
+        source = {'buffer': audio, 'mimetype': 'audio/wav'}
+        response = deepgram.transcription.sync_prerecorded(source, {'punctuate': True})
+        print(json.dumps(response, indent=4))
+
+main()
+```
+
+#### Transcribe an Existing File or Pre-recorded Audio Asynchronously
+
 ```python
 from deepgram import Deepgram
 import asyncio, json

deepgram/_utils.py

@@ -1,6 +1,8 @@
 from typing import Any, Union, Optional, IO, Mapping, Tuple, List, cast
 import aiohttp
 import urllib.parse
+import urllib.request
+import urllib.error
 import io
 import json
 import re
@@ -117,6 +119,48 @@ async def attempt():
     return await attempt()
 
 
+def _sync_request(
+    path: str, options: Options,
+    method: str = 'GET', payload: Payload = None,
+    headers: Optional[Mapping[str, str]] = None
+) -> Any:
+    if headers is None:
+        headers = {}
+    destination = cast(str, options.get('api_url', DEFAULT_ENDPOINT)) + path
+    updated_headers = _prepare_headers(options, headers)
+
+    def attempt():
+        req = urllib.request.Request(
+            destination, 
+            data=_normalize_payload(payload), 
+            headers=updated_headers, 
+            method=method)
+        try:
+            with urllib.request.urlopen(req) as resp:
+                content = resp.read().strip()
+                if not content:
+                    return None
+                body = json.loads(content)
+                if body.get('error'):
+                    raise Exception(f'DG: {content}')
+                return body
+        except urllib.error.URLError as exc:
+            raise (Exception(f'DG: {exc}') if exc.status < 500 else exc)
+
+    tries = RETRY_COUNT
+    while tries > 0:
+        try:
+            return attempt()
+        except urllib.error.URLError as exc:
+            if isinstance(payload, io.IOBase):
+                raise exc # stream is now invalid as payload
+                # the way aiohttp handles streaming form data
+                # means that just seeking this back still runs into issues
+            tries -= 1
+            continue
+    return attempt()
+
+
 async def _socket_connect(
     path: str, options: Options, headers: Optional[Mapping[str, str]] = None
 ) -> websockets.client.WebSocketClientProtocol:

deepgram/transcription.py

@@ -9,11 +9,11 @@
                      TranscriptionSource, PrerecordedTranscriptionResponse,
                      LiveTranscriptionResponse, Metadata, EventHandler)
 from ._enums import LiveTranscriptionEvent
-from ._utils import _request, _make_query_string, _socket_connect
+from ._utils import _request, _sync_request, _make_query_string, _socket_connect
 
 
 class PrerecordedTranscription:
-    """This class provides an interface for doing transcription on prerecorded audio files."""
+    """This class provides an interface for doing transcription asynchronously on prerecorded audio files."""
 
     _root = "/listen"
 
@@ -63,6 +63,58 @@ async def __call__(
         )
 
 
+class SyncPrerecordedTranscription:
+    """This class provides an interface for doing transcription synchronously on prerecorded audio files."""
+
+    _root = "/listen"
+
+    def __init__(self, options: Options,
+                 transcription_options: PrerecordedOptions) -> None:
+        """
+        This function initializes the options and transcription_options for the PrerecordedTranscription class.
+
+        :param options:Options: Used to Pass in the options for the transcription.
+        :param transcription_options:PrerecordedOptions: Used to Specify the transcription options for a prerecorded audio file.
+        :return: Nothing.
+
+        """
+
+        self.options = options
+        self.transcription_options = transcription_options
+
+    def __call__(
+        self, source: TranscriptionSource
+    ) -> PrerecordedTranscriptionResponse:
+
+        """
+        The __call__ function is a special method that allows the class to be called
+        as a function. This is useful for creating instances of the class, where we can
+        call `SyncPrerecordedTranscription()` and pass in arguments to set up an instance of
+        the class. For example:
+        
+            sync_prerecorded_transcription = SyncPrerecordedTranscription(...)
+        
+        :param source:TranscriptionSource: Used to Pass in the audio file.
+        :return: A `prerecordedtranscriptionresponse` object, which contains the transcription results.
+        
+        """
+
+        if 'buffer' in source and 'mimetype' not in source:
+            raise Exception(
+                'DG: Mimetype must be provided if the source is bytes'
+            )
+        payload = cast(
+            Union[bytes, Dict],
+            source.get('buffer', {'url': source.get('url')})
+        )
+        content_type = cast(str, source.get('mimetype', 'application/json'))
+        return _sync_request(
+            f'{self._root}{_make_query_string(self.transcription_options)}',
+            self.options, method='POST', payload=payload,
+            headers={'Content-Type': content_type}
+        )
+
+
 class LiveTranscription:
     """
     This class allows you to perform live transcription by connecting to Deepgram's Transcribe Streaming API.
@@ -283,6 +335,21 @@ async def prerecorded(
             self.options, full_options
         )(source)
 
+
+    def sync_prerecorded(
+        self, source: TranscriptionSource,
+        options: PrerecordedOptions = None, **kwargs
+    ) -> PrerecordedTranscriptionResponse:
+        """Retrieves a transcription for an already-existing audio file,
+        local or web-hosted."""
+        if options is None:
+            options = {}
+        full_options = cast(PrerecordedOptions, {**options, **kwargs})
+        return SyncPrerecordedTranscription(
+            self.options, full_options
+        )(source)
+
+
     async def live(
         self, options: LiveOptions = None, **kwargs
     ) -> LiveTranscription: