Duplicate from KPatrick/PaddleSpeechASR

Co-authored-by: KPatrick <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+---
+title: PaddleSpeechASR
+emoji: 🌖
+colorFrom: green
+colorTo: red
+sdk: gradio
+app_file: app.py
+pinned: false
+duplicated_from: KPatrick/PaddleSpeechASR
+---
+
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,41 @@
+import gradio as gr
+import librosa
+import numpy as np
+import paddlehub as hub
+from paddlenlp import Taskflow
+from paddlespeech.cli import ASRExecutor
+import soundfile as sf
+
+# asr_model = hub.Module(name='u2_conformer_aishell')
+asr_executor = ASRExecutor()
+text_correct_model = Taskflow("text_correction")
+punc_model = hub.Module(name='auto_punc')
+
+
+def speech_recognize(file):
+    data, sr = librosa.load(file)
+    if sr != 16000:
+        data = librosa.resample(data, sr, 16000)
+    sf.write(file, data, samplerate=16000)
+
+    print(f'[Audio Input] shape: {data.shape}, dtype: {data.dtype}, file: {file}')
+    # text = asr_model.speech_recognize(file, device='cpu')
+    text = asr_executor(file)
+    text_correction = text_correct_model(text)[0]
+    cor_text, errors = text_correction['target'], text_correction['errors']
+    print(f'[Text Correction] errors: {errors}')
+    punc_text = punc_model.add_puncs(cor_text, device='cpu')[0]
+
+    ret = ''
+    ret += f'[ASR] {text}\n'
+    ret += f'[COR] {cor_text}\n'
+    ret += f'[PUN] {punc_text}'
+    return ret
+
+
+iface = gr.Interface(
+    fn=speech_recognize, 
+    inputs=gr.inputs.Audio(source="microphone", type='filepath'),
+    outputs="text",
+)
+iface.launch()

packages.txt

@@ -0,0 +1,5 @@
+libsndfile1
+sox
+ffmpeg
+libsm6
+libxext6

requirements.txt

@@ -0,0 +1,9 @@
+paddlepaddle==2.2.0
+paddleaudio==0.1.0a0
+paddlespeech==0.1.0rc0
+paddlehub
+paddlenlp
+pypinyin
+SoundFile
+librosa
+opencv-python-headless