mirror/gradio
2
0
Fork 0
mirror of https://github.com/gradio-app/gradio.git synced 2024-11-27 01:40:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

Hotfix for: stt_or_tts demo (#7332)

Browse Source 
* fix

* add changeset

* add changeset

* notebooks

---------

Co-authored-by: gradio-pr-bot <gradio-pr-bot@users.noreply.github.com>
This commit is contained in:
Abubakar Abid 2024-02-06 14:34:02 -08:00 committed by GitHub
parent edfd05d18d
commit 8bb0ce2e40
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
.changeset/petite-years-call.md Normal file
View File

@ -0,0 +1,5 @@
---
"gradio": patch
---
feat:Hotfix for: `stt_or_tts` demo

2
demo/stt_or_tts/run.ipynb
View File

@ -1 +1 @@
{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: stt_or_tts"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "\n", "tts_examples = [\n", " \"I love learning machine learning\",\n", " \"How do you do?\",\n", "]\n", "\n", "tts_demo = gr.load(\n", " \"huggingface/facebook/fastspeech2-en-ljspeech\",\n", " title=None,\n", " examples=tts_examples,\n", " description=\"Give me something to say!\",\n", " cache_examples=False\n", ")\n", "\n", "stt_demo = gr.load(\n", " \"huggingface/facebook/wav2vec2-base-960h\",\n", " title=None,\n", " inputs=\"mic\",\n", " description=\"Let me try to guess what you're saying!\",\n", ")\n", "\n", "demo = gr.TabbedInterface([tts_demo, stt_demo], [\"Text-to-speech\", \"Speech-to-text\"])\n", "\n", "if __name__ == \"__main__\":\n", " demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}
{"cells": [{"cell_type": "markdown", "id": "302934307671667531413257853548643485645", "metadata": {}, "source": ["# Gradio Demo: stt_or_tts"]}, {"cell_type": "code", "execution_count": null, "id": "272996653310673477252411125948039410165", "metadata": {}, "outputs": [], "source": ["!pip install -q gradio "]}, {"cell_type": "code", "execution_count": null, "id": "288918539441861185822528903084949547379", "metadata": {}, "outputs": [], "source": ["import gradio as gr\n", "\n", "tts_examples = [\n", " \"I love learning machine learning\",\n", " \"How do you do?\",\n", "]\n", "\n", "tts_demo = gr.load(\n", " \"huggingface/facebook/fastspeech2-en-ljspeech\",\n", " title=None,\n", " examples=tts_examples,\n", " description=\"Give me something to say!\",\n", ")\n", "\n", "stt_demo = gr.load(\n", " \"huggingface/facebook/wav2vec2-base-960h\",\n", " title=None,\n", " inputs=gr.Microphone(type=\"filepath\"),\n", " description=\"Let me try to guess what you're saying!\",\n", ")\n", "\n", "demo = gr.TabbedInterface([tts_demo, stt_demo], [\"Text-to-speech\", \"Speech-to-text\"])\n", "\n", "if __name__ == \"__main__\":\n", " demo.launch()\n"]}], "metadata": {}, "nbformat": 4, "nbformat_minor": 5}

3
demo/stt_or_tts/run.py
View File

@ -10,13 +10,12 @@ tts_demo = gr.load(
title=None,
examples=tts_examples,
description="Give me something to say!",
cache_examples=False
)
stt_demo = gr.load(
"huggingface/facebook/wav2vec2-base-960h",
title=None,
inputs="mic",
inputs=gr.Microphone(type="filepath"),
description="Let me try to guess what you're saying!",
)

2
gradio/external.py
View File

@ -153,7 +153,7 @@ def from_model(model_name: str, hf_token: str | None, alias: str | None, **kwarg
fn = custom_post_binary
# example model: facebook/wav2vec2-base-960h
elif p == "automatic-speech-recognition":
inputs = components.Audio(sources=["upload"], type="filepath", label="Input")
inputs = components.Audio(type="filepath", label="Input")
outputs = components.Textbox(label="Output")
examples = [
"https://gradio-builds.s3.amazonaws.com/demo-files/audio_sample.wav"