sana123 NeuralInternet commited on
Commit
57ada76
0 Parent(s):

Duplicate from NeuralInternet/Audio-to-Text_Playground

Browse files

Co-authored-by: Neural Inτerneτ <NeuralInternet@users.noreply.huggingface.co>

Files changed (5) hide show
  1. .gitattributes +34 -0
  2. README.md +15 -0
  3. app.py +109 -0
  4. packages.txt +1 -0
  5. requirements.txt +3 -0
.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ title: Audio-to-Text Playground
3
+ emoji: 🤫
4
+ colorFrom: indigo
5
+ colorTo: red
6
+ sdk: gradio
7
+ sdk_version: 3.9.1
8
+ app_file: app.py
9
+ pinned: false
10
+ tags:
11
+ - whisper-event
12
+ duplicated_from: NeuralInternet/Audio-to-Text_Playground
13
+ ---
14
+
15
+ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
app.py ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import torch
2
+
3
+ import gradio as gr
4
+ import pytube as pt
5
+ from transformers import pipeline
6
+
7
+ MODEL_NAME = "openai/whisper-large-v2"
8
+
9
+ device = 0 if torch.cuda.is_available() else "cpu"
10
+
11
+ pipe = pipeline(
12
+ task="automatic-speech-recognition",
13
+ model=MODEL_NAME,
14
+ chunk_length_s=30,
15
+ device=device,
16
+ )
17
+
18
+
19
+ all_special_ids = pipe.tokenizer.all_special_ids
20
+ transcribe_token_id = all_special_ids[-5]
21
+ translate_token_id = all_special_ids[-6]
22
+
23
+
24
+ def transcribe(microphone, file_upload, task):
25
+ warn_output = ""
26
+ if (microphone is not None) and (file_upload is not None):
27
+ warn_output = (
28
+ "WARNING: You've uploaded an audio file and used the microphone. "
29
+ "The recorded file from the microphone will be used and the uploaded audio will be discarded.\n"
30
+ )
31
+
32
+ elif (microphone is None) and (file_upload is None):
33
+ return "ERROR: You have to either use the microphone or upload an audio file"
34
+
35
+ file = microphone if microphone is not None else file_upload
36
+
37
+ pipe.model.config.forced_decoder_ids = [[2, transcribe_token_id if task=="transcribe" else translate_token_id]]
38
+
39
+ text = pipe(file)["text"]
40
+
41
+ return warn_output + text
42
+
43
+
44
+ def _return_yt_html_embed(yt_url):
45
+ video_id = yt_url.split("?v=")[-1]
46
+ HTML_str = (
47
+ f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe>'
48
+ " </center>"
49
+ )
50
+ return HTML_str
51
+
52
+
53
+ def yt_transcribe(yt_url, task):
54
+ yt = pt.YouTube(yt_url)
55
+ html_embed_str = _return_yt_html_embed(yt_url)
56
+ stream = yt.streams.filter(only_audio=True)[0]
57
+ stream.download(filename="audio.mp3")
58
+
59
+ pipe.model.config.forced_decoder_ids = [[2, transcribe_token_id if task=="transcribe" else translate_token_id]]
60
+
61
+ text = pipe("audio.mp3")["text"]
62
+
63
+ return html_embed_str, text
64
+
65
+
66
+ demo = gr.Blocks()
67
+
68
+ mf_transcribe = gr.Interface(
69
+ fn=transcribe,
70
+ inputs=[
71
+ gr.inputs.Audio(source="microphone", type="filepath", optional=True),
72
+ gr.inputs.Audio(source="upload", type="filepath", optional=True),
73
+ gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe"),
74
+ ],
75
+ outputs="text",
76
+ layout="horizontal",
77
+ theme="huggingface",
78
+ title="Audio-to-Text Playground: Transcribe Audio",
79
+ description=(
80
+ "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the"
81
+ f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
82
+ " of arbitrary length."
83
+ ),
84
+ allow_flagging="never",
85
+ )
86
+
87
+ yt_transcribe = gr.Interface(
88
+ fn=yt_transcribe,
89
+ inputs=[
90
+ gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
91
+ gr.inputs.Radio(["transcribe", "translate"], label="Task", default="transcribe")
92
+ ],
93
+ outputs=["html", "text"],
94
+ layout="horizontal",
95
+ theme="huggingface",
96
+ title="Audio-to-Text Playground: Transcribe YouTube",
97
+ description=(
98
+ "Transcribe long-form YouTube videos with the click of a button! Demo uses the checkpoint"
99
+ f" [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe video files of"
100
+ " arbitrary length."
101
+ ),
102
+ allow_flagging="never",
103
+ )
104
+
105
+ with demo:
106
+ gr.TabbedInterface([mf_transcribe, yt_transcribe], ["Transcribe Audio", "Transcribe YouTube"])
107
+
108
+ demo.launch(enable_queue=True)
109
+
packages.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ ffmpeg
requirements.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ git+https://github.com/huggingface/transformers
2
+ torch
3
+ pytube