Upload 3 files

README.md

@@ -1,13 +1,11 @@
+
 ---
-title: Avishkaar Check
-emoji: 🏃
-colorFrom: yellow
-colorTo: red
+title: automatic-speech-recognition 
+emoji: 🔥
+colorFrom: indigo
+colorTo: indigo
 sdk: gradio
 sdk_version: 3.35.2
-app_file: app.py
+app_file: run.py
 pinned: false
-license: openrail
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,37 +1,17 @@
-import torch
-import torchaudio
-from transformers import Wav2Vec2ForCTC, Wav2Vec2Tokenizer
 import gradio as gr
-
-# Load pre-trained model and tokenizer
-model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-large-960h")
-tokenizer = Wav2Vec2Tokenizer.from_pretrained("facebook/wav2vec2-large-960h")
-
-def transcribe_speech(audio_file):
-    # Load and convert audio file to waveform
-    waveform, _ = torchaudio.load(audio_file)
-
-    # Preprocess waveform
-    input_values = tokenizer(waveform, return_tensors="pt").input_values
-
-    # Perform inference
-    with torch.no_grad():
-        logits = model(input_values).logits
-
-    # Get predicted transcription
-    predicted_ids = torch.argmax(logits, dim=-1)
-    transcription = tokenizer.batch_decode(predicted_ids)[0]
-
-    return transcription
-
-# Define Gradio interface
-def speech_recognition(audio_file):
-    transcription = transcribe_speech(audio_file)
-    return transcription
-
-inputs = gr.inputs.Audio(type="file", label="Upload Audio File")
-outputs = gr.outputs.Textbox(label="Transcription")
-interface = gr.Interface(fn=speech_recognition, inputs=inputs, outputs=outputs)
-
-# Run the Gradio interface
-interface.launch()
+import os
+
+# save your HF API token from https:/hf.co/settings/tokens as an env variable to avoid rate limiting
+auth_token = os.getenv("auth_token")
+
+# automatically load the interface from a HF model 
+# you can remove the api_key parameter if you don't care about rate limiting. 
+demo = gr.Interface.load(
+    "huggingface/facebook/wav2vec2-base-960h",
+    title="Speech-to-text",
+    inputs="mic",
+    description="Let me try to guess what you're saying!",
+    api_key=auth_token
+)
+
+demo.launch()

run.py

@@ -0,0 +1,17 @@
+import gradio as gr
+import os
+
+# save your HF API token from https:/hf.co/settings/tokens as an env variable to avoid rate limiting
+auth_token = os.getenv("auth_token")
+
+# automatically load the interface from a HF model 
+# you can remove the api_key parameter if you don't care about rate limiting. 
+demo = gr.load(
+    "huggingface/facebook/wav2vec2-base-960h",
+    title="Speech-to-text",
+    inputs="mic",
+    description="Let me try to guess what you're saying!",
+    hf_token=auth_token
+)
+
+demo.launch()