Spaces:
Runtime error
Runtime error
| import streamlit as st | |
| from st_audiorec import st_audiorec #pip install streamlit-audiorec | |
| import nemo.collections.asr as nemo_asr | |
| from pydub import AudioSegment | |
| import subprocess | |
| import io | |
| import os | |
| import uuid | |
| def get_model(): | |
| try: | |
| os.makedirs("audio_cache") | |
| except: | |
| pass | |
| if not os.path.exists("./hi_am_model"): | |
| print("Downloading Hindi AM") | |
| download = subprocess.run(["wget","-P","./hi_am_model","https://storage.googleapis.com/vakyansh-open-models/conformer_models/hindi/filtered_v1_ssl_2022-07-08_19-43-25/Conformer-CTC-BPE-Large.nemo"],capture_output=True, text=True) | |
| if download.returncode != 0: | |
| raise Exception(f"Hindi Model Download Failed: {download.stderr}") | |
| else: | |
| print('Downloaded Hindi AM') | |
| if not os.path.exists("./en_am_model"): | |
| print("Downloading English AM") | |
| download = subprocess.run(["wget","-P","./en_am_model","https://storage.googleapis.com/vakyansh-open-models/conformer_models/english/2022-09-13_15-50-48/Conformer-CTC-BPE-Large.nemo"],capture_output=True, text=True) | |
| if download.returncode != 0: | |
| raise Exception(f"English Model Download Failed: {download.stderr}") | |
| else: | |
| print('Downloaded English AM') | |
| try: | |
| en_asr_model = nemo_asr.models.EncDecCTCModelBPE.restore_from("./en_am_model/Conformer-CTC-BPE-Large.nemo")# /home/tanmay/zb/en_Conformer-CTC-BPE-Large.nemo | |
| hi_asr_model = nemo_asr.models.EncDecCTCModelBPE.restore_from("./hi_am_model/Conformer-CTC-BPE-Large.nemo") #/home/tanmay/zb/hi_Conformer-CTC-BPE-Large.nemo | |
| except Exception as e: | |
| print("ERROR Loading Model... ",e) | |
| exit (1) | |
| return en_asr_model, hi_asr_model | |
| en_asr_model, hi_asr_model = get_model() | |
| st.title("💬 Vocalize: Empower Your Voice ") | |
| language = st.selectbox('Enter Your Preferred Language.', ('English', 'Hindi')) | |
| """ | |
| Hi cord the audio, and get the transcription in real time! | |
| Note: Works best for smaller audios | |
| """ | |
| # col1, col2 = st.columns(2) | |
| st.header("Transcribe Your Voice Using Mic") | |
| wav_audio_data = st_audiorec() | |
| if wav_audio_data: | |
| audio_location = "audio_cache/" + str(uuid.uuid4()) + ".wav" | |
| audio_file = io.BytesIO(wav_audio_data) | |
| audio = AudioSegment.from_file(audio_file) | |
| audio = audio.set_sample_width(2) | |
| audio = audio.set_channels(1) | |
| audio = audio.set_frame_rate(16000) | |
| audio.export(audio_location, format="wav") | |
| if language == "Hindi": | |
| text = hi_asr_model.transcribe([audio_location], logprobs=False)[0] | |
| st.write(text) | |
| else: | |
| text = en_asr_model.transcribe([audio_location], logprobs=False)[0] | |
| print(text) | |
| st.write("Transcription:") | |
| st.write(text) | |
| st.header("Transcribe Files") | |
| uploaded_file = st.file_uploader("Upload Your Recording", disabled=False) | |
| if uploaded_file is not None: | |
| # Store the uploaded file: | |
| audio_location = "audio_cache/" + str(uuid.uuid4()) + ".wav" | |
| with open(audio_location, "wb") as f: | |
| f.write(uploaded_file.getvalue()) | |
| is_translate = st.button("Click Me For Translation") | |
| # Trigger transcription: | |
| if is_translate: | |
| if language == "Hindi": | |
| with st.spinner(): | |
| text = hi_asr_model.transcribe([audio_location], logprobs=False)[0] | |
| print(text) | |
| else: | |
| with st.spinner(): | |
| text = en_asr_model.transcribe([audio_location], logprobs=False)[0] | |
| print(text) | |
| st.write(text) | |