Hugging Face's logo

Spaces:
kennethli319
/
ASR-toolbox
Runtime error

App Files Community
ASR-toolbox
File size: 4,772 Bytes 
7c6ede0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
 
from nemo.collections.asr.models import EncDecRNNTBPEModel
import gradio as gr
from pydub import AudioSegment

device = "cuda" if torch.cuda.is_available() else "cpu"
MODEL_NAME="nvidia/parakeet-rnnt-1.1b"


def get_transcripts(audio_path):

    model = EncDecRNNTBPEModel.from_pretrained(model_name="nvidia/parakeet-rnnt-1.1b").to(device)
    model.eval()
    text = model.transcribe([audio_path])[0][0]
    return text

article = (
    "<p style='text-align: center'>"
    "<a href='https://huggingface.co/nvidia/parakeet-rnnt-1.1b' target='_blank'>🎙️ Learn more about Parakeet model</a> | "
    "<a href='https://arxiv.org/abs/2305.05084' target='_blank'>📚 FastConformer paper</a> | "
    "<a href='https://github.com/NVIDIA/NeMo' target='_blank'>🧑‍💻 Repository</a>"
    "</p>"
)
examples = [
    ["data/conversation.wav"],
    ["data/id10270_5r0dWxy17C8-00001.wav"],
]

def _return_yt_html_embed(yt_url):
    video_id = yt_url.split("?v=")[-1]
    HTML_str = (
        f'<center> <iframe width="500" height="320" src="https://www.youtube.com/embed/{video_id}"> </iframe>'
        " </center>"
    )
    return HTML_str

def download_yt_audio(yt_url, filename):
    info_loader = youtube_dl.YoutubeDL()
    
    try:
        info = info_loader.extract_info(yt_url, download=False)
    except youtube_dl.utils.DownloadError as err:
        raise gr.Error(str(err))
    
    file_length = info["duration_string"]
    file_h_m_s = file_length.split(":")
    file_h_m_s = [int(sub_length) for sub_length in file_h_m_s]
    
    if len(file_h_m_s) == 1:
        file_h_m_s.insert(0, 0)
    if len(file_h_m_s) == 2:
        file_h_m_s.insert(0, 0)
    file_length_s = file_h_m_s[0] * 3600 + file_h_m_s[1] * 60 + file_h_m_s[2]
    
    if file_length_s > YT_LENGTH_LIMIT_S:
        yt_length_limit_hms = time.strftime("%HH:%MM:%SS", time.gmtime(YT_LENGTH_LIMIT_S))
        file_length_hms = time.strftime("%HH:%MM:%SS", time.gmtime(file_length_s))
        raise gr.Error(f"Maximum YouTube length is {yt_length_limit_hms}, got {file_length_hms} YouTube video.")
    
    ydl_opts = {"outtmpl": filename, "format": "worstvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best"}
    
    with youtube_dl.YoutubeDL(ydl_opts) as ydl:
        try:
            ydl.download([yt_url])
        except youtube_dl.utils.ExtractorError as err:
            raise gr.Error(str(err))


def yt_transcribe(yt_url, task, max_filesize=75.0):
    html_embed_str = _return_yt_html_embed(yt_url)

    with tempfile.TemporaryDirectory() as tmpdirname:
        filepath = os.path.join(tmpdirname, "video.mp4")
        download_yt_audio(yt_url, filepath)
        audio = AudioSegment.from_file(filepath)
        wav_filepath = os.path.join(tmpdirname, "audio.wav")
        audio.export(wav_filepath, format="wav")

    text = get_transcripts(wav_filepath)
    return html_embed_str, text


demo = gr.Blocks()

mf_transcribe = gr.Interface(
    fn=transcribe,
    inputs=[
        gr.inputs.Audio(source="microphone", type="filepath", optional=True)
    ],
    outputs="text",
    layout="horizontal",
    theme="huggingface",
    title="Parakeet RNNT 1.1B: Transcribe Audio",
    description=(
        "Transcribe microphone or audio inputs with the click of a button! Demo uses the"
        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and NVIDIA NeMo to transcribe audio files"
        " of arbitrary length."
    ),
    allow_flagging="never",
)

file_transcribe = gr.Interface(
    fn=transcribe,
    inputs=[
        gr.inputs.Audio(source="upload", type="filepath", optional=True, label="Audio file"),
    ],
    outputs="text",
    layout="horizontal",
    theme="huggingface",
    title="Parakeet RNNT 1.1B: Transcribe Audio",
    description=(
        "Transcribe microphone or audio inputs with the click of a button! Demo uses the"
        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and NVIDIA NeMo to transcribe audio files"
        " of arbitrary length."
    ),
    allow_flagging="never",
)

yt_transcribe = gr.Interface(
    fn=yt_transcribe,
    inputs=[
        gr.inputs.Textbox(lines=1, placeholder="Paste the URL to a YouTube video here", label="YouTube URL"),
    ],
    outputs=["html", "text"],
    layout="horizontal",
    theme="huggingface",
    title="Parakeet RNNT 1.1B: Transcribe Audio",
    description=(
        "Transcribe microphone or audio inputs with the click of a button! Demo uses the"
        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and NVIDIA NeMo to transcribe audio files"
        " of arbitrary length."
    ),
    allow_flagging="never",
)

with demo:
    gr.TabbedInterface([mf_transcribe, file_transcribe], ["Microphone", "Audio file"])

demo.launch(enable_queue=True)