Merge pull request #37 from slashml/deepgram

Deepgram

Author: eff-kay

CHANGELOG.md

@@ -2,6 +2,14 @@
 All notable changes to `slashml-python-client` aka `slashml` will be documented in this file.
 This project adheres to [Semantic Versioning](https://semver.org/).
 
+## 0.0.7 - 2023-05-11
+
+### Added
+- Added deepgram model for SpeechToText service
+
+### Fixed
+- Fixed a bug in examples by replacing verbs with  `submit_job`
+
 ## 0.0.6 - 2023-05-11
 
 ### Changed

examples/speech_to_text_async.py

@@ -12,7 +12,7 @@ def speech_to_text(audio_filepath, service_provider, api_key):
     print(f"file uploaded: {uploaded_file}")
 
     # Submit transcription request
-    job = model.transcribe(
+    job = model.submit_job(
         uploaded_file["upload_url"], service_provider=service_provider
     )
 
@@ -33,7 +33,7 @@ def speech_to_text(audio_filepath, service_provider, api_key):
 # Replace `API_KEY` with your SlasML API token. This example still runs without
 # the API token but usage will be limited
 API_KEY = None
-service_provider = SpeechToText.ServiceProvider.ASSEMBLY
+service_provider = SpeechToText.ServiceProvider.DEEPGRAM
 audio_filepath = "test.mp3"
 
 # Find all the service providers that we support by running the choices() method

examples/speech_to_text_sync.py

@@ -3,7 +3,7 @@
 # Replace `API_KEY` with your SlasML API token. This example still runs without
 # the API token but usage will be limited
 API_KEY = None
-service_provider = SpeechToText.ServiceProvider.AWS
+service_provider = SpeechToText.ServiceProvider.DEEPGRAM
 audio_filepath = "test.mp3"
 
 # Find all the service providers that we support by running the choices() method

examples/summarize_async.py

@@ -6,7 +6,7 @@ def summarize(text, service_provider, api_key):
     model = TextSummarization(api_key=api_key)
 
     # Submit request
-    job = model.summarize(text=text, service_provider=service_provider)
+    job = model.submit_job(text=text, service_provider=service_provider)
 
     assert job.status != "ERROR", f"{job}"
     print(f"Job ID: {job.id}")

examples/text_to_speech_async copy.py examples/text_to_speech_async.pyexamples/text_to_speech_async copy.py renamed to examples/text_to_speech_async.py

@@ -1,4 +1,5 @@
 from slashml import TextToSpeech
+import time
 
 # Replace `API_KEY` with your SlasML API token. This example still runs without
 # the API token but usage will be limited
@@ -13,7 +14,15 @@
 model = TextToSpeech(api_key=API_KEY)
 
 # Submit request
-job = model.speechify(text=input_text, service_provider=service_provider)
+job = model.submit_job(text=input_text, service_provider=service_provider)
 print(job)
 
-print (f"\nYou can access the audio file here: {job.audio_url}")
+# check job status
+response = model.status(job.id, service_provider=service_provider)
+
+while response.status == "IN_PROGRESS":
+    print(f"Response = {response}. Retrying in 30 seconds")
+    time.sleep(30)
+    response = model.status(job.id, service_provider=service_provider)
+
+print (f"\nYou can access the audio file here: {response.audio_url}")

slashml/speech_to_text.py

@@ -9,6 +9,7 @@ class ServiceProvider(Enum):
         ASSEMBLY = "assembly"
         AWS = "aws"
         WHISPER = "whisper"
+        DEEPGRAM = 'deepgram'
 
         @classmethod
         def choices(cls):
@@ -55,10 +56,10 @@ def execute(self, upload_url: str, service_provider: ServiceProvider):
         # check job status
         response = getTaskStatus(self._base_url, self._headers, job.id, service_provider)
 
-        while response.status == "IN_PROGRESS":
-            time.sleep(5)
-            response = getTaskStatus(self._base_url, self._headers, job.id, service_provider)
-            print(f"Response = {response}. Retrying in 5 seconds")
+        # while response.status == "IN_PROGRESS":
+        time.sleep(5)
+        response = getTaskStatus(self._base_url, self._headers, job.id, service_provider)
+        print(f"Response = {response}. Retrying in 5 seconds")
 
         return response