initial commit

app.py

@@ -0,0 +1,116 @@
+import concurrent
+
+from transformers import pipeline
+import gradio as gr
+import torch
+import torchaudio
+from resemble_enhance.enhancer.inference import denoise, enhance
+
+from flore200_codes import flores_codes
+
+# Check if CUDA is available
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Translation pipeline
+translation_model = "oza75/nllb-600M-mt-french-bambara"
+translator = pipeline("translation", model=translation_model, max_length=512)
+
+# Text-to-Speech pipeline
+tts_model = "oza75/bambara-tts-male-001"
+tts = pipeline("text-to-speech", model=tts_model, device=device)
+
+
+# Function to translate text to Bambara
+def translate_to_bambara(text, src_lang):
+    translation = translator(text, src_lang=src_lang, tgt_lang="bam_Latn")
+    return translation[0]['translation_text']
+
+
+# Function to convert text to speech
+def text_to_speech(bambara_text):
+    speech = tts(bambara_text)
+    audio, sr = speech['audio'], speech['sampling_rate']
+    audio = torch.from_numpy(audio).mean(dim=0)
+
+    return audio, sr
+
+
+# Function to enhance speech
+def enhance_speech(audio_array, sampling_rate, solver, nfe, tau, denoise_before_enhancement):
+    solver = solver.lower()
+    nfe = int(nfe)
+    lambd = 0.9 if denoise_before_enhancement else 0.1
+
+    def denoise_audio():
+        return denoise(audio_array, sampling_rate, device)
+
+    def enhance_audio():
+        return enhance(audio_array, sampling_rate, device, nfe=nfe, solver=solver, lambd=lambd, tau=tau)
+
+    with concurrent.futures.ThreadPoolExecutor() as executor:
+        future_denoise = executor.submit(denoise_audio)
+        future_enhance = executor.submit(enhance_audio)
+
+        denoised_audio, new_sr1 = future_denoise.result()
+        enhanced_audio, new_sr2 = future_enhance.result()
+
+        # Convert to numpy and return
+        return (new_sr1, denoised_audio.cpu().numpy()), (new_sr2, enhanced_audio.cpu().numpy())
+
+
+# Define the Gradio interface
+def _fn(src_lang, text, solver="Midpoint", nfe=64, prior_temp=0.5, denoise_before_enhancement=False):
+    source_lang = flores_codes[src_lang]
+
+    # Step 1: Translate the text to Bambara
+    bambara_text = translate_to_bambara(text, source_lang)
+
+    # Step 2: Convert the translated text to speech
+    audio_array, sampling_rate = text_to_speech(bambara_text)
+
+    # Step 3: Enhance the audio
+    denoised_audio, enhanced_audio = enhance_speech(
+        audio_array,
+        sampling_rate,
+        solver,
+        nfe,
+        prior_temp,
+        denoise_before_enhancement
+    )
+
+    # Return all outputs
+    return bambara_text, (sampling_rate, audio_array.cpu().numpy()), denoised_audio, enhanced_audio
+
+
+def main():
+    lang_codes = list(flores_codes.keys())
+
+    # Build Gradio app
+    app = gr.Interface(
+        fn=_fn,
+        inputs=[
+            gr.Dropdown(label="Source Language", choices=lang_codes, value='French'),
+            gr.Textbox(label="Text to Translate"),
+            gr.Dropdown(
+                choices=["Midpoint", "RK4", "Euler"], value="Midpoint",
+                label="ODE Solver (Midpoint is recommended)"
+            ),
+            gr.Slider(minimum=1, maximum=128, value=64, step=1, label="Number of Function Evaluations"),
+            gr.Slider(minimum=0, maximum=1, value=0.5, step=0.01, label="Prior Temperature"),
+            gr.Checkbox(value=False, label="Denoise Before Enhancement")
+        ],
+        outputs=[
+            gr.Textbox(label="Translated Text"),
+            gr.Audio(label="Original TTS Audio"),
+            gr.Audio(label="Denoised Audio"),
+            gr.Audio(label="Enhanced Audio")
+        ],
+        title="Bambara Translation and Text to Speech with Audio Enhancement",
+        description="Translate text to Bambara and convert it to speech with options to enhance audio quality."
+    )
+
+    app.launch()
+
+
+if __name__ == "__main__":
+    main()

flore200_codes.py

@@ -0,0 +1,211 @@
+codes_as_string = '''Acehnese (Arabic script)	ace_Arab
+Acehnese (Latin script)	ace_Latn
+Mesopotamian Arabic	acm_Arab
+Ta’izzi-Adeni Arabic	acq_Arab
+Tunisian Arabic	aeb_Arab
+Afrikaans	afr_Latn
+South Levantine Arabic	ajp_Arab
+Akan	aka_Latn
+Amharic	amh_Ethi
+North Levantine Arabic	apc_Arab
+Modern Standard Arabic	arb_Arab
+Modern Standard Arabic (Romanized)	arb_Latn
+Najdi Arabic	ars_Arab
+Moroccan Arabic	ary_Arab
+Egyptian Arabic	arz_Arab
+Assamese	asm_Beng
+Asturian	ast_Latn
+Awadhi	awa_Deva
+Central Aymara	ayr_Latn
+South Azerbaijani	azb_Arab
+North Azerbaijani	azj_Latn
+Bashkir	bak_Cyrl
+Bambara	bam_Latn
+Balinese	ban_Latn
+Belarusian	bel_Cyrl
+Bemba	bem_Latn
+Bengali	ben_Beng
+Bhojpuri	bho_Deva
+Banjar (Arabic script)	bjn_Arab
+Banjar (Latin script)	bjn_Latn
+Standard Tibetan	bod_Tibt
+Bosnian	bos_Latn
+Buginese	bug_Latn
+Bulgarian	bul_Cyrl
+Catalan	cat_Latn
+Cebuano	ceb_Latn
+Czech	ces_Latn
+Chokwe	cjk_Latn
+Central Kurdish	ckb_Arab
+Crimean Tatar	crh_Latn
+Welsh	cym_Latn
+Danish	dan_Latn
+German	deu_Latn
+Southwestern Dinka	dik_Latn
+Dyula	dyu_Latn
+Dzongkha	dzo_Tibt
+Greek	ell_Grek
+English	eng_Latn
+Esperanto	epo_Latn
+Estonian	est_Latn
+Basque	eus_Latn
+Ewe	ewe_Latn
+Faroese	fao_Latn
+Fijian	fij_Latn
+Finnish	fin_Latn
+Fon	fon_Latn
+French	fra_Latn
+Friulian	fur_Latn
+Nigerian Fulfulde	fuv_Latn
+Scottish Gaelic	gla_Latn
+Irish	gle_Latn
+Galician	glg_Latn
+Guarani	grn_Latn
+Gujarati	guj_Gujr
+Haitian Creole	hat_Latn
+Hausa	hau_Latn
+Hebrew	heb_Hebr
+Hindi	hin_Deva
+Chhattisgarhi	hne_Deva
+Croatian	hrv_Latn
+Hungarian	hun_Latn
+Armenian	hye_Armn
+Igbo	ibo_Latn
+Ilocano	ilo_Latn
+Indonesian	ind_Latn
+Icelandic	isl_Latn
+Italian	ita_Latn
+Javanese	jav_Latn
+Japanese	jpn_Jpan
+Kabyle	kab_Latn
+Jingpho	kac_Latn
+Kamba	kam_Latn
+Kannada	kan_Knda
+Kashmiri (Arabic script)	kas_Arab
+Kashmiri (Devanagari script)	kas_Deva
+Georgian	kat_Geor
+Central Kanuri (Arabic script)	knc_Arab
+Central Kanuri (Latin script)	knc_Latn
+Kazakh	kaz_Cyrl
+Kabiyè	kbp_Latn
+Kabuverdianu	kea_Latn
+Khmer	khm_Khmr
+Kikuyu	kik_Latn
+Kinyarwanda	kin_Latn
+Kyrgyz	kir_Cyrl
+Kimbundu	kmb_Latn
+Northern Kurdish	kmr_Latn
+Kikongo	kon_Latn
+Korean	kor_Hang
+Lao	lao_Laoo
+Ligurian	lij_Latn
+Limburgish	lim_Latn
+Lingala	lin_Latn
+Lithuanian	lit_Latn
+Lombard	lmo_Latn
+Latgalian	ltg_Latn
+Luxembourgish	ltz_Latn
+Luba-Kasai	lua_Latn
+Ganda	lug_Latn
+Luo	luo_Latn
+Mizo	lus_Latn
+Standard Latvian	lvs_Latn
+Magahi	mag_Deva
+Maithili	mai_Deva
+Malayalam	mal_Mlym
+Marathi	mar_Deva
+Minangkabau (Arabic script)	min_Arab
+Minangkabau (Latin script)	min_Latn
+Macedonian	mkd_Cyrl
+Plateau Malagasy	plt_Latn
+Maltese	mlt_Latn
+Meitei (Bengali script)	mni_Beng
+Halh Mongolian	khk_Cyrl
+Mossi	mos_Latn
+Maori	mri_Latn
+Burmese	mya_Mymr
+Dutch	nld_Latn
+Norwegian Nynorsk	nno_Latn
+Norwegian Bokmål	nob_Latn
+Nepali	npi_Deva
+Northern Sotho	nso_Latn
+Nuer	nus_Latn
+Nyanja	nya_Latn
+Occitan	oci_Latn
+West Central Oromo	gaz_Latn
+Odia	ory_Orya
+Pangasinan	pag_Latn
+Eastern Panjabi	pan_Guru
+Papiamento	pap_Latn
+Western Persian	pes_Arab
+Polish	pol_Latn
+Portuguese	por_Latn
+Dari	prs_Arab
+Southern Pashto	pbt_Arab
+Ayacucho Quechua	quy_Latn
+Romanian	ron_Latn
+Rundi	run_Latn
+Russian	rus_Cyrl
+Sango	sag_Latn
+Sanskrit	san_Deva
+Santali	sat_Olck
+Sicilian	scn_Latn
+Shan	shn_Mymr
+Sinhala	sin_Sinh
+Slovak	slk_Latn
+Slovenian	slv_Latn
+Samoan	smo_Latn
+Shona	sna_Latn
+Sindhi	snd_Arab
+Somali	som_Latn
+Southern Sotho	sot_Latn
+Spanish	spa_Latn
+Tosk Albanian	als_Latn
+Sardinian	srd_Latn
+Serbian	srp_Cyrl
+Swati	ssw_Latn
+Sundanese	sun_Latn
+Swedish	swe_Latn
+Swahili	swh_Latn
+Silesian	szl_Latn
+Tamil	tam_Taml
+Tatar	tat_Cyrl
+Telugu	tel_Telu
+Tajik	tgk_Cyrl
+Tagalog	tgl_Latn
+Thai	tha_Thai
+Tigrinya	tir_Ethi
+Tamasheq (Latin script)	taq_Latn
+Tamasheq (Tifinagh script)	taq_Tfng
+Tok Pisin	tpi_Latn
+Tswana	tsn_Latn
+Tsonga	tso_Latn
+Turkmen	tuk_Latn
+Tumbuka	tum_Latn
+Turkish	tur_Latn
+Twi	twi_Latn
+Central Atlas Tamazight	tzm_Tfng
+Uyghur	uig_Arab
+Ukrainian	ukr_Cyrl
+Umbundu	umb_Latn
+Urdu	urd_Arab
+Northern Uzbek	uzn_Latn
+Venetian	vec_Latn
+Vietnamese	vie_Latn
+Waray	war_Latn
+Wolof	wol_Latn
+Xhosa	xho_Latn
+Eastern Yiddish	ydd_Hebr
+Yoruba	yor_Latn
+Yue Chinese	yue_Hant
+Chinese (Simplified)	zho_Hans
+Chinese (Traditional)	zho_Hant
+Standard Malay	zsm_Latn
+Zulu	zul_Latn'''
+
+codes_as_string = codes_as_string.split('\n')
+
+flores_codes = {}
+for code in codes_as_string:
+    lang, lang_code = code.split('\t')
+    flores_codes[lang] = lang_code

requirements.txt

@@ -0,0 +1,5 @@
+transformers
+gradio
+torch
+torchaudio
+resemble-enhance