feat(app): add example and small mods

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text

app.py

@@ -20,16 +20,14 @@ ACCEPTED_LANGUAGE_BEHAVIOUR = [
 
 
 def transcribe(
-    audio_url: str = None,
     audio: str = None,
-    video: str = None,
     language_behaviour: str = ACCEPTED_LANGUAGE_BEHAVIOUR[2],
     language: str = "english",
 ) -> dict:
     """
     This function transcribes audio to text using the Gladia API. 
     It sends a request to the API with the given audio file or audio URL, and returns the transcribed text.
-    Find your api key at gladia.io
+    Get your api key at gladia.io !
 
     Parameters:
     audio_url (str): The URL of the audio file to transcribe. If audio_url is provided, audio file will be ignored.
@@ -58,10 +56,6 @@ def transcribe(
         "language_behaviour": (None, language_behaviour),
     }
 
-    # priority given to the video
-    if video:
-        audio = video
-
     # priority given to the audio or video
     if audio:
         files["audio"] = (audio, open(audio, "rb"), "audio/wav")
@@ -107,25 +101,16 @@ def transcribe(
 iface = gr.Interface(
     title="Gladia.io fast audio transcription",
     description="""Gladia.io Whisper large-v2 fast audio transcription API
-    is able to perform fast audio transcription for any audio / video or url format.<br/><br/>
-    However it's prefered for faster performance to provide <br/>
-    wav 16KHz with 16b encoding (pcm_u16be) to avoid further the conversion time.<br/>
-    "automatic single language" language discovery behavior may also<br/>
-    slow down (just a little bit - talking about ms) the process.
-    <br/>
-    Here is a benchmark ran on multiple Speech-To-Text providers
-    ![Benchmarks](https://storage.gra.cloud.ovh.net/v1/AUTH_90df0bdc74f749ce86783e6550b1e4aa/public-files/benchmark.png)<br/>
-    Join our [Slack](https://gladia-io.slack.com) to discuss with us.<br/><br/>
-    Get your own API key on [Gladia.io](https://gladia.io/) during free alpha
+    is able to perform fast audio transcriptions for any audio / video.
+    For more details and a benchmark ran on multiple Speech-To-Text providers, please visit
+    [our post](https://medium.com/@gladia.io/gladia-alpha-launch-redefining-what-s-possible-with-speech-to-text-ai-686dd4312a86) on Medium.
+    <br/><br/>
+    You are more than welcome to join our [Slack](https://gladia-io.slack.com) to discuss with us
+    and also don't forget to get your own API key on [Gladia.io](https://gladia.io/) during the free alpha !
     """,
     fn=transcribe,
     inputs=[
-        gr.Textbox(
-            lines=1,
-            label="Audio/Video url to transcribe",
-        ),
         gr.Audio(label="or Audio file to transcribe", source="upload", type="filepath"),
-        gr.Video(label="or Video file to transcribe", source="upload", type="filepath"),
         gr.Dropdown(
             label="""Language transcription behaviour:\n
         If "manual", the language field must be provided and the API will transcribe the audio in the given language.
@@ -144,6 +129,10 @@ iface = gr.Interface(
         ),
     ],
     outputs="json",
+    examples=[
+        ["examples/good.will.hunting.wav", ACCEPTED_LANGUAGE_BEHAVIOUR[1], "english"],
+        ["examples/wolf.of.wall.street.wav", ACCEPTED_LANGUAGE_BEHAVIOUR[1], "english"],
+    ],
 )
 iface.queue()
 iface.launch()

examples/good.will.hunting.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:981492667ceb174e8a5d272ed68ad0a5198d98d836ff955b5e3b45d105d2a422
+size 14251502

examples/wolf.of.wall.street.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1283c0fa5e3829a7f6630c17d73647e494c39fc56f0eec8331ffaf0df23162
+size 1601526